Added Application Files

Dockerfile

@@ -0,0 +1,47 @@
+# Use the official Ubuntu 20.04 image as the base
+FROM ubuntu:20.04
+
+# Set environment variables
+ENV LANG=C.UTF-8 LC_ALL=C.UTF-8
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    wget \
+    bzip2 \
+    ca-certificates \
+    curl \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Miniconda
+ENV CONDA_DIR=/opt/conda
+RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O /tmp/miniconda.sh && \
+    /bin/bash /tmp/miniconda.sh -b -p $CONDA_DIR && \
+    rm /tmp/miniconda.sh
+
+# Add Miniconda to the PATH
+ENV PATH=$CONDA_DIR/bin:$PATH
+
+# Create a Conda environment using Mamba
+COPY environment.yml /tmp/environment.yml
+RUN conda env create -n caNanoLibrarian -f /tmp/environment.yml && \
+    rm /tmp/environment.yml
+
+# Activate the Conda environment by default
+ENV PATH=$CONDA_DIR/envs/caNanoLibrarian/bin:$PATH
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy your application files
+COPY . /app
+
+# Expose the container port
+EXPOSE 5000
+
+# Set environment variables (optional)
+ENV FLASK_APP=app.py
+ENV FLASK_RUN_HOST=0.0.0.0
+
+# Define the command to run your application
+CMD [ "python", "app.py" ]

LICENSE

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+                            Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+                       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+                     END OF TERMS AND CONDITIONS
+
+            How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<https://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<https://www.gnu.org/licenses/why-not-lgpl.html>.

README.md

@@ -1,11 +1,15 @@
 ---
-title: CaNanoLibrarian
-emoji: 📊
-colorFrom: green
+title: caNanoLibrarian
+emoji: 🐳
+colorFrom: blue
 colorTo: purple
 sdk: docker
+app_port: 7860
+app_file: app.py
 pinned: false
-license: apache-2.0
 ---
+# caNanoLibrarian
+This is the backend of the caNanoLibrarian app, which is a LLM based natural language searching experience for a structure database.
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+We have the application on https://cananolibrarian.azurewebsites.net/login, if you want to play with it, the passcode is caNanoLibrarian_DEMO_wkrh_6152023*.
+We have a limited budget for this project, please let us know if you want to continue explore it when the GPT complains about limit. Thanks.

__init__.py

@@ -0,0 +1,19 @@
+import os
+import sys
+
+dir_path = os.path.abspath(os.getcwd())
+utils_path = dir_path + "\\src\\app_utils"
+database_tool_path = dir_path + "\\src\\database_creation"
+src_path = dir_path + "\\src"
+data_path = dir_path + "\\data"
+sys.path.append(utils_path)
+sys.path.append(src_path)
+sys.path.append(data_path)
+sys.path.append(database_tool_path)
+
+# COMPLETIONS_MODEL = "gpt-3.5-turbo"
+# EMBEDDING_MODEL = "text-embedding-ada-002"
+# config_dir = dir_path + "\\src\\utils"
+# config = configparser.ConfigParser()
+# config.read(os.path.join(config_dir, 'gpt_local_config.cfg'))
+# openai.api_key = config.get('token', 'GPT_TOKEN')

app.py

@@ -0,0 +1,88 @@
+import os
+import sys
+import time
+import openai
+import configparser
+import sqlite3
+
+dir_path = os.path.abspath(os.getcwd())
+
+utils_path = dir_path + "/src/app_utils"
+src_path = dir_path + "/src"
+sys.path.append(utils_path)
+sys.path.append(src_path)
+
+from flask import Flask, render_template, request, redirect, url_for, g
+import application_utils as au
+
+COMPLETIONS_MODEL = "gpt-3.5-turbo"
+EMBEDDING_MODEL = "text-embedding-ada-002"
+config_dir = utils_path
+config = configparser.ConfigParser()
+config.read(os.path.join(config_dir, 'gpt_local_config.cfg'))
+# openai.api_key = config.get('token', 'GPT_TOKEN')
+openai.api_key = os.environ.get("GPT_TOKEN")
+
+
+# Specify the path to db file
+db_name = 'caNanoData_Public.db'
+
+COMPLETIONS_API_PARAMS = {
+    # We use temperature of 0.0 because it gives
+    # the most predictable, factual answer.
+    "temperature": 0.0,
+    "max_tokens": 400,
+    "model": "gpt-3.5-turbo"
+}
+
+app = Flask("caNanoLibrarian")
+
+
+def get_db():
+    db = getattr(g, '_database', None)
+    if db is None:
+        db = g._database = sqlite3.connect('caNanoData_Public.db')
+    return db
+
+
+@app.teardown_appcontext
+def close_db(exception):
+    db = getattr(g, '_database', None)
+    if db is not None:
+        db.close()
+
+
+@app.template_filter('nl2br')
+def nl2br_filter(s):
+    return s.replace('\n', '<br>')
+
+
+@app.route('/', methods=['GET', 'POST'])
+def index():
+
+    connection = get_db()
+
+    user_input = ""
+    # processed_input = None
+    if request.method == 'POST':
+        user_input = request.form['user_input']
+        result_df, query = au.custom_query(
+                        user_input, connection,
+                        GPT4=True,
+                        print_prompt=False,
+                        print_query=True,
+                        print_time=False
+                    )
+        return render_template(
+            'index.html',
+            processed_input=result_df.to_html(
+                classes='dataframe custom-style',
+                index=False),
+            source_sections=query,
+            user_input=user_input)
+
+    return render_template('index.html')
+
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=7860)

environment.yml

@@ -0,0 +1,12 @@
+name: caNanoLibrarian
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - python=3.10.9
+  - openai=0.27.5
+  - numpy=1.24.3
+  - pandas=2.0.1
+  - tiktoken=0.4.0
+  - configparser=5.3.0
+  - flask=2.3.2

src/app_utils/application_utils.py

@@ -0,0 +1,154 @@
+import sql_utils as su
+import gpt_utils as gu
+import time
+
+
+def database_structure_strings():
+
+    NanoEntDes_structure = "{table:NanoEntDes,attributes:" + \
+        "[ID(Primary),NanoEntity,Description]}"
+
+    NanoEntCom_structure = "{table:NanoEntCom,attributes:" + \
+        "[ID(Primary),NanoEntity,Composition,CompositionType," + \
+        "MolecularWeight,PubChemID]}"
+
+    FuncEntDes_structure = "{table: FuncEntDes, attributes:" + \
+        "[ID(Primary),FunctionEntity,FunctionEntityType," + \
+        "Description,ActivationMethod,pubChemID," + \
+        "MolarMass,MolarMassUnit]}"
+
+    FuncEntFunction_structure = "{table: FuncEntFunction," + \
+        "attributes:[ID(Primary),FunctionEntiry,Function," + \
+        "FunctionDescription]}"
+
+    ChemAsso_structure = "{table: ChemAsso, attributes:" + \
+        "[ID(Primary),AssociationType,BondType,Description," + \
+        "dataId,ComposingElementNameA,ComposingElementNameB," + \
+        "CompositiontypeB,CompositiontypeA,DomainElementNameB," + \
+        "DomainElementNameA,DomainAssociationId,ComposingElemetIdB," + \
+        "ComposingElemetIdA,ComposingElementTypeA,EntityDisplayNameB," + \
+        "ComposingElementTypeB,EntityDisplayNameA,AttachmentId}"
+
+    GeneralInfo_structure = "{table:GeneralInfo,attributes:" + \
+        "[ID(Primary),sampleName,createdYear,createdMonth]}"
+
+    SampleKeywords_structure = "{table:SampleKeyWords,attributes:" + \
+        "[ID(Primary),sampleName,SampleKeyWord]}"
+
+    PublicationInfo_structure = "{table:PublicationInfo," + \
+        "attributes:[ID(Primary),PMID,year,title,author," + \
+        "journal,publicationCategories,description]}"
+
+    PublicationKeyWords_structure = "{table:PublicationKeyWords," + \
+        "attributes:[ID(Primary),sampleName,SampleKeyWord]}"
+
+    CharacterizationInfo_structure = "{table:CharacterizationInfo," + \
+        "attributes:[ID(Primary),CharType,CharName," + \
+        "AssayType,Protocol, " + \
+        "DesignDescription,AnalysisAndConclusion]}"
+
+    CharExpConfig_structure = "{table:CharExpConfig," + \
+        "attributes:[ID(Primary),CharType,CharName," + \
+        "AssayType,ExpConfigTechnique, " + \
+        "ExpConfigInstruments,ExpConfigDescription]}"
+
+    CharResultDescriptions_structure = "{table:CharResultDescriptions," + \
+        "attributes:[ID(Primary),CharType,CharName," + \
+        "AssayType,CharResultDescription]}"
+
+    CharResultKeywords_structure = "{table:CharResultKeywords," + \
+        "attributes:[ID(Primary),CharType,CharName," + \
+        "AssayType,CharResultKeyword]}"
+
+    CharResultTables_structure = "{table:CharResultTables," + \
+        "attributes:[ID(Primary),CharType,CharName," + \
+        "AssayType,CharTable]}"
+
+    note1 = "NanoEntCom should not be used to count unique " + \
+        "NanoEntity\ncount composition should only use composition table"
+
+    note2 = "ALL tables shoud join on ID. Table NanoEntDes and " + \
+        "NanoEntCom share key NanoEntity, " + \
+        "FuncEntDes and FuncEntFunction share FunctionEntity key, " + \
+        "ChemAsso does not have other common keys with other tables."
+
+    note3 = "Strictly reference to table name and columns in this context. "
+
+    Overall_structure = [
+        "\n",
+        NanoEntDes_structure,
+        NanoEntCom_structure,
+        FuncEntDes_structure,
+        FuncEntFunction_structure,
+        ChemAsso_structure,
+        GeneralInfo_structure,
+        SampleKeywords_structure,
+        PublicationInfo_structure,
+        PublicationKeyWords_structure,
+        CharacterizationInfo_structure,
+        CharExpConfig_structure,
+        CharResultDescriptions_structure,
+        CharResultKeywords_structure,
+        CharResultTables_structure,
+        note1,
+        note2,
+        note3
+    ]
+
+    Overall_structure_string = "\n".join(Overall_structure)
+
+    return Overall_structure_string
+
+
+def custom_query(
+    question,
+    connection,
+    GPT4=True,
+    print_prompt=False,
+    print_token=False,
+    print_query=False,
+    print_time=False
+):
+
+    stucture = database_structure_strings()
+
+    context_token_count = gu.num_tokens_from_string(
+        stucture
+    )
+
+    prompt = su.sql_prompt(
+        question,
+        stucture
+    )
+
+    prompt_token_count = gu.num_tokens_from_string(prompt)
+
+    if print_prompt:
+        print(prompt)
+
+    if print_token:
+        print(f"\nContext token count: {context_token_count}")
+        print(f"Prompt token count: {prompt_token_count}")
+
+    start_time = time.time()
+
+    if GPT4:
+        query = gu.quick_ask(prompt, model_num=0)
+    else:
+        query = gu.quick_ask(prompt, model_num=1)
+
+    if print_query:
+        print("\n============= The Query is: ===============\n")
+        print(query)
+        print("\n===========================================\n")
+
+    result_df = su.submit_querry(query, connection)
+    # End the timer
+    end_time = time.time()
+    # Calculate the execution time
+    execution_time = end_time - start_time
+    # Print the execution time
+    if print_time:
+        print("\nExecution Time:", execution_time, "seconds")
+
+    return result_df, query

src/app_utils/gpt_local_config.cfg

@@ -0,0 +1,5 @@
+[token]
+GPT_TOKEN =
+[model]
+model_for_fine_tune = davinci
+model_for_chat = gpt-3.5-turbo

src/app_utils/gpt_utils.py

@@ -0,0 +1,44 @@
+import configparser
+import os
+import openai
+import tiktoken
+import os.path
+
+
+config_dir = os.path.dirname(__file__)
+config = configparser.ConfigParser()
+config.read(os.path.join(config_dir, 'gpt_local_config.cfg'))
+
+# openai.api_key = config.get('token', 'GPT_TOKEN')
+openai.api_key = os.environ.get("GPT_TOKEN")
+
+model_for_chat = config.get('model', 'model_for_chat')
+
+
+# https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
+def num_tokens_from_string(string: str, model="gpt-3.5-turbo") -> int:
+    """Returns the number of tokens in a text string."""
+    encoding = tiktoken.encoding_for_model(model)
+    num_tokens = len(encoding.encode(string))
+
+    return num_tokens
+
+
+def quick_ask(prompt,
+              model_num=1,
+              max_tokens=500):
+
+    model = ["gpt-4-0314",
+             "gpt-3.5-turbo",
+             "gpt-4-32k",
+             "gpt-3.5-turbo-16k"]
+
+    response = openai.ChatCompletion.create(
+            model=model[model_num],
+            messages=[{"role": "user",
+                       "content": prompt}],
+            temperature=0,
+            max_tokens=max_tokens
+            )
+
+    return response.choices[0]['message']['content']

src/app_utils/sql_utils.py

@@ -0,0 +1,103 @@
+import pandas as pd
+import sqlite3
+
+
+def show_table_columns(connection, table):
+
+    query = f"PRAGMA table_info({table});"
+    table_columns = simple_querry(
+        connection,
+        query
+    )
+
+    for item in table_columns:
+        print(f"Column: {item[1]}, Type: {item[2]}")
+
+
+def construct_db(
+        db_name,
+        overview_dict
+        ):
+
+    # Create a SQLite database connection
+    conn = sqlite3.connect(db_name)
+
+    for key in overview_dict:
+        overview_dict[key].to_sql(
+            key,
+            conn,
+            if_exists='replace',
+            index=False)
+
+    # Close the database connection
+    conn.close()
+
+    return "Done"
+
+
+def submit_querry(
+        query,
+        connection
+        ):
+
+    try:
+        # Create a cursor object to execute SQL queries
+        cursor = connection.cursor()
+
+        # Execute the SQL query
+        cursor.execute(query)
+
+        # Fetch the column names
+        column_names = [description[0] for description in cursor.description]
+
+        # Fetch all the results
+        results = cursor.fetchall()
+
+        # Combine the column names with the query result
+        # header = ','.join(column_names)
+
+        # Close the cursor and the connection
+        cursor.close()
+
+        # Create a DataFrame from the results
+        df = pd.DataFrame(results, columns=column_names)
+
+        # Return the DataFrame
+        return df
+
+    except Exception as e:
+        # Return the error message if an exception occurs
+        error_message = str(e)
+        df = pd.DataFrame({'Error': [error_message]})
+        return df
+
+
+def sql_prompt(question, stucture):
+    header = "select appropriate table(s), write me a sql query to:\n"
+    tail = " return sql query only."
+
+    prompt = header + \
+        question + " " + \
+        "\n\n(context: the table structure is: " + \
+        stucture + ")" + \
+        tail
+
+    return prompt
+
+
+def simple_querry(connection, querry):
+    cursor = connection.cursor()
+
+    # Execute the SQL query
+    cursor.execute(querry)
+
+    # Fetch all the results
+    results = cursor.fetchall()
+
+    return results
+
+
+def show_tables(connection):
+    show_tables = "SELECT name\nFROM sqlite_master\nWHERE type = 'table'"
+    tables = simple_querry(connection, show_tables)
+    print(tables)

src/database_creation/characterization_info_creation.py

@@ -0,0 +1,404 @@
+import csv
+import sql_utils as su
+from tqdm.notebook import tqdm_notebook
+
+
+def create_characterization_dt_tables(connection):
+
+    CharacterizationInfo_str = "CREATE TABLE IF NOT EXISTS " + \
+        "CharacterizationInfo " + \
+        "(ID INT, CharType VARCHAR(150), CharName VARCHAR(150), " + \
+        "AssayType VARCHAR(150), Protocol TEXT, " + \
+        "DesignDescription TEXT, AnalysisAndConclusion TEXT);"
+
+    CharExpConfig_str = "CREATE TABLE IF NOT EXISTS " + \
+        "CharExpConfig " + \
+        "(ID INT, CharType VARCHAR(150), CharName VARCHAR(150), " + \
+        "AssayType VARCHAR(150), ExpConfigTechnique TEXT, " + \
+        "ExpConfigInstruments TEXT, ExpConfigDescription TEXT);"
+
+    CharResultDescriptions_str = "CREATE TABLE IF NOT EXISTS " + \
+        "CharResultDescriptions " + \
+        "(ID INT, CharType VARCHAR(150), CharName VARCHAR(150), " + \
+        "AssayType VARCHAR(150), CharResultDescription TEXT);"
+
+    CharResultKeywords_str = "CREATE TABLE IF NOT EXISTS " + \
+        "CharResultKeywords " + \
+        "(ID INT, CharType VARCHAR(150), CharName VARCHAR(150), " + \
+        "AssayType VARCHAR(150), CharResultKeyword VARCHAR(150)); "
+
+    CharResultTables_str = "CREATE TABLE IF NOT EXISTS " + \
+        "CharResultTables " + \
+        "(ID INT, CharType VARCHAR(150), CharName VARCHAR(150), " + \
+        "AssayType VARCHAR(150), CharTable TEXT); "
+
+    table_creation_querys = [
+        CharacterizationInfo_str,
+        CharExpConfig_str,
+        CharResultDescriptions_str,
+        CharResultKeywords_str,
+        CharResultTables_str
+        ]
+
+    for query in table_creation_querys:
+        results = su.simple_querry(
+            connection,
+            query
+            )
+        if len(results) == 0:
+            print("Table Exists")
+        else:
+            print(results)
+
+    su.show_tables(connection)
+
+
+def characterization_to_sql(
+        characterization_dt,
+        connection
+):
+
+    total_ids = len(characterization_dt)
+    no_sample_list = []
+    with tqdm_notebook(
+        total=total_ids,
+        desc='Processing',
+        unit='ID'
+    ) as progress_bar:
+        cursor = connection.cursor()
+
+        for ID in characterization_dt:
+            sample_info = characterization_dt[ID]
+
+            for CharType_info in sample_info:
+                if 'type' not in CharType_info:
+                    print('There is no characterization with your sample.')
+                    no_sample_list.append([ID, CharType_info])
+                    continue
+                CharType = CharType_info['type']
+                CharType_Info_Assay = CharType_info['charsByAssayType']
+                for CharName in CharType_Info_Assay:
+                    CharName_infos = CharType_Info_Assay[CharName]
+                    for charname_info in CharName_infos:
+                        displayableItems = charname_info['displayableItems']
+                        # Create a cursor object
+                        for item in displayableItems:
+                            if item['name'] == 'Assay Type':
+                                AssayType = item['value']
+
+                            if item['name'] == 'Protocol':
+                                Protocol = item['value']
+
+                            if item['name'] == 'Design Description':
+                                DesignDescription = item['value']
+
+                            if item['name'] == 'Experiment Configurations':
+                                exp_config_list = item['value']
+
+                            if item['name'] == 'Characterization Results':
+                                char_results = item['value']
+
+                            if item['name'] == 'Analysis and Conclusion':
+                                AnalysisAndConclusion = item['value']
+
+                        n_row = len(exp_config_list[0]['Technique'])
+                        for i in range(n_row):
+                            ExpConfigTechnique = exp_config_list[
+                                0
+                            ]['Technique'][i]
+
+                            ExpConfigInstruments = exp_config_list[
+                                1
+                            ]['Instruments'][i]
+
+                            ExpConfigDescription = exp_config_list[
+                                2
+                            ]['Description'][i]
+
+                            # Write to NanoEntDes
+                            CharExpConfig_insert = (
+                                ID,
+                                CharType,
+                                CharName,
+                                AssayType,
+                                ExpConfigTechnique,
+                                ExpConfigInstruments,
+                                ExpConfigDescription
+                                )
+
+                            # Execute a SELECT statement to check
+                            # if the entry already exists
+
+                            search_query = "SELECT COUNT(*) FROM " + \
+                                "CharExpConfig" + \
+                                " WHERE ID = ?" + \
+                                " AND CharType = ?" + \
+                                " AND CharName = ?" + \
+                                " AND AssayType = ?" + \
+                                " AND ExpConfigTechnique = ?" + \
+                                " AND ExpConfigInstruments = ?;"
+
+                            cursor.execute(
+                                search_query,
+                                CharExpConfig_insert[:6]
+                            )
+                            count = cursor.fetchone()[0]
+
+                            # Check the count to determine
+                            # if the entry exists
+                            if count == 0:
+                                # Entry does not exist, proceed
+                                # with insertion
+                                insert_query = "INSERT INTO " + \
+                                    "CharExpConfig " + \
+                                    "(ID, " + \
+                                    "CharType, " + \
+                                    "CharName, " + \
+                                    "AssayType, " + \
+                                    "ExpConfigTechnique, " + \
+                                    "ExpConfigInstruments, " + \
+                                    "ExpConfigDescription) " + \
+                                    "VALUES (?, ?, ?, ?, ?, ?, ?)"
+                                cursor.execute(
+                                    insert_query,
+                                    CharExpConfig_insert
+                                )
+                                connection.commit()
+
+                        for char_result in char_results:
+                            if 'Data and Conditions' in char_result:
+                                table_list = char_result[
+                                    'Data and Conditions'
+                                ]
+                                CharTable = ""
+                                for item in table_list:
+                                    tsc = ",".join(
+                                        item[
+                                            'value'
+                                        ]
+                                    )
+                                    CharTable += tsc
+                                    CharTable += ";"
+                                    # Write to NanoEntDes
+                                    CRTables_insert = (
+                                        ID,
+                                        CharType,
+                                        CharName,
+                                        AssayType,
+                                        CharTable
+                                        )
+
+                                    # Execute a SELECT
+                                    # statement to check
+                                    # if the entry already exists
+
+                                    search_query = "SELECT " + \
+                                        "COUNT(*) FROM " + \
+                                        "CharResultTables" + \
+                                        " WHERE ID = ?" + \
+                                        " AND CharType = ?" + \
+                                        " AND CharName = ?" + \
+                                        " AND AssayType = ?;"
+
+                                    cursor.execute(
+                                        search_query,
+                                        CRTables_insert[:4]
+                                    )
+                                    count = cursor.fetchone()[0]
+
+                                    # Check the count to determine
+                                    # if the entry exists
+                                    if count == 0:
+                                        # Entry does not exist, proceed
+                                        # with insertion
+                                        insert_query = "INSERT " + \
+                                            "INTO " + \
+                                            "CharResultTables " + \
+                                            "(ID, " + \
+                                            "CharType, " + \
+                                            "CharName, " + \
+                                            "AssayType, " + \
+                                            "CharTable) " + \
+                                            "VALUES (?, ?, ?, ?, ?)"
+                                        cursor.execute(
+                                            insert_query,
+                                            CRTables_insert
+                                        )
+                                        connection.commit()
+                            if 'Files' in char_result:
+                                file_list = char_result[
+                                    'Files'
+                                ]
+
+                                for char_file in file_list:
+                                    if 'description' in char_file:
+                                        CRDes = char_file[
+                                            'description'
+                                        ]
+                                    else:
+                                        CRDes = "None"
+
+                                    if 'keywordsString' in char_file:
+                                        CRKWstr_ls = char_file[
+                                            'keywordsString'
+                                        ].split(",")
+                                    else:
+                                        CRKWstr_ls = list("None")
+
+                                    CRDes_insert = (
+                                        ID,
+                                        CharType,
+                                        CharName,
+                                        AssayType,
+                                        CRDes
+                                        )
+
+                                    # Execute a SELECT
+                                    # statement to check
+                                    # if the entry already exists
+
+                                    search_query = "SELECT " + \
+                                        "COUNT(*) FROM " + \
+                                        "CharResultDescriptions" + \
+                                        " WHERE ID = ?" + \
+                                        " AND CharType = ?" + \
+                                        " AND CharName = ?" + \
+                                        " AND AssayType = ?;"
+
+                                    cursor.execute(
+                                        search_query,
+                                        CRDes_insert[:4]
+                                    )
+                                    count = cursor.fetchone()[0]
+
+                                    # Check the count to determine
+                                    # if the entry exists
+                                    if count == 0:
+                                        # Entry does not exist, proceed
+                                        # with insertion
+                                        insert_query = "INSERT " + \
+                                            "INTO " + \
+                                            "CharResultDescriptions" +\
+                                            " (ID, " + \
+                                            "CharType, " + \
+                                            "CharName, " + \
+                                            "AssayType, " + \
+                                            "CharResultDescription" + \
+                                            ") " + \
+                                            "VALUES (?, ?, ?, ?, ?)"
+
+                                        cursor.execute(
+                                            insert_query,
+                                            CRDes_insert
+                                        )
+                                        connection.commit()
+
+                                    for CRKW in CRKWstr_ls:
+                                        CRKW_insert = (
+                                            ID,
+                                            CharType,
+                                            CharName,
+                                            AssayType,
+                                            CRKW
+                                        )
+
+                                        # Execute a SELECT
+                                        # statement to check
+                                        # if the entry already exists
+
+                                        search_query = "SELECT " + \
+                                            "COUNT(*) FROM " + \
+                                            "CharResultKeywords" + \
+                                            " WHERE ID = ?" + \
+                                            " AND CharType = ?" + \
+                                            " AND CharName = ?" + \
+                                            " AND AssayType = ?" + \
+                                            " AND " + \
+                                            "CharResultKeyword = ?;"
+
+                                        cursor.execute(
+                                            search_query,
+                                            CRKW_insert
+                                        )
+                                        count = cursor.fetchone()[0]
+
+                                        # Check the count to determine
+                                        # if the entry exists
+                                        if count == 0:
+                                            # Entry does not exist,
+                                            # proceed
+                                            # with insertion
+                                            insert_query = "INSERT " +\
+                                                "INTO " + \
+                                                "CharResultKeywords" +\
+                                                " (ID, " + \
+                                                "CharType, " + \
+                                                "CharName, " + \
+                                                "AssayType, " + \
+                                                "CharResultKeyword" + \
+                                                ") " + \
+                                                "VALUES (?, ?, " + \
+                                                "?, ?, ?)"
+
+                                            cursor.execute(
+                                                insert_query,
+                                                CRKW_insert
+                                            )
+                                            connection.commit()
+
+                        # Write to NanoEntDes
+                        CharacterizationInfo_insert = (
+                            ID,
+                            CharType,
+                            CharName,
+                            AssayType,
+                            Protocol,
+                            DesignDescription,
+                            AnalysisAndConclusion
+                            )
+
+                        # Execute a SELECT statement to check
+                        # if the entry already exists
+
+                        search_query = "SELECT COUNT(*) FROM " + \
+                            "CharacterizationInfo" + \
+                            " WHERE ID = ?" + \
+                            " AND CharType = ?" + \
+                            " AND CharName = ?" + \
+                            " AND AssayType = ?" + \
+                            " AND Protocol = ?;"
+
+                        cursor.execute(
+                            search_query,
+                            CharacterizationInfo_insert[:5]
+                        )
+                        count = cursor.fetchone()[0]
+
+                        # Check the count to determine if the entry exists
+                        if count == 0:
+                            # Entry does not exist, proceed with insertion
+                            insert_query = "INSERT INTO " + \
+                                "CharacterizationInfo " + \
+                                "(ID, " + \
+                                "CharType, " + \
+                                "CharName, " + \
+                                "AssayType, " + \
+                                "Protocol, " + \
+                                "DesignDescription, " + \
+                                "AnalysisAndConclusion) " + \
+                                "VALUES (?, ?, ?, ?, ?, ?, ?)"
+                            cursor.execute(
+                                insert_query,
+                                CharacterizationInfo_insert
+                            )
+                            connection.commit()
+            progress_bar.update(1)
+    cursor.close()
+    no_sample_csv = 'no_characterization.csv'
+    # Specify the filename for the CSV file
+
+    with open(no_sample_csv, 'w', newline='') as file:
+        writer = csv.writer(file)
+        writer.writerows(no_sample_list)
+
+    print(f"CSV file '{no_sample_csv}' has been created.")

src/database_creation/chemical_association_creation.py

@@ -0,0 +1,149 @@
+import data_utils as du
+import sql_utils as su
+from tqdm.notebook import tqdm_notebook
+
+
+def create_ChemAsso_tables(connection):
+
+    table_String_ChemAssoName = "CREATE TABLE IF NOT EXISTS ChemAsso (" + \
+        "ID INT, " + \
+        "AssociationType VARCHAR(150), " + \
+        "BondType VARCHAR(150), " + \
+        "Description TEXT, " + \
+        "dataId INT, " + \
+        "ComposingElementNameA VARCHAR(150), " + \
+        "ComposingElementNameB VARCHAR(150), " + \
+        "CompositiontypeB VARCHAR(150), " + \
+        "CompositiontypeA VARCHAR(150), " + \
+        "DomainElementNameB VARCHAR(150), " + \
+        "DomainElementNameA VARCHAR(150), " + \
+        "DomainAssociationId INT, " + \
+        "ComposingElemetIdB INT, " + \
+        "ComposingElemetIdA INT, " + \
+        "ComposingElementTypeA VARCHAR(150), " + \
+        "EntityDisplayNameB VARCHAR(150), " + \
+        "ComposingElementTypeB VARCHAR(150), " + \
+        "EntityDisplayNameA VARCHAR(150), " + \
+        "AttachmentId INT);"
+
+    table_creation_querys = [
+        table_String_ChemAssoName
+        ]
+
+    for query in table_creation_querys:
+        results = su.simple_querry(
+            connection,
+            query
+            )
+        if len(results) == 0:
+            print("Table Exists")
+        else:
+            print(results)
+    su.show_tables(connection)
+
+
+def chemicalassociation_to_sql(
+        composition_dt,
+        connection
+):
+
+    chemicalassociation_dt = {}
+
+    du.parse_dictionary(
+        composition_dt,
+        "chemicalassociation",
+        chemicalassociation_dt
+        )
+
+    total_ids = len(chemicalassociation_dt)
+
+    with tqdm_notebook(
+        total=total_ids,
+        desc='Processing',
+        unit='ID'
+    ) as progress_bar:
+
+        # Create a cursor object
+        cursor = connection.cursor()
+
+        for ID in chemicalassociation_dt:
+            sample_info = chemicalassociation_dt[ID]
+            for AssociationType in sample_info:
+                AssociationType_info = sample_info[AssociationType]
+                for Entry in AssociationType_info:
+                    # Create a cursor object
+                    elements = Entry['AssocitedElements']
+
+                    # Write to NanoEntCom
+                    ChemAsso_insert = (
+                        ID,
+                        AssociationType,
+                        Entry['BondType'],
+                        Entry['Description'],
+                        Entry['dataId'],
+                        elements['ComposingElementNameA'],
+                        elements['ComposingElementNameB'],
+                        elements['CompositiontypeB'],
+                        elements['CompositiontypeA'],
+                        elements['DomainElementNameB'],
+                        elements['DomainElementNameA'],
+                        elements['DomainAssociationId'],
+                        elements['ComposingElemetIdB'],
+                        elements['ComposingElemetIdA'],
+                        elements['ComposingElementTypeA'],
+                        elements['EntityDisplayNameB'],
+                        elements['ComposingElementTypeB'],
+                        elements['EntityDisplayNameA'],
+                        Entry['AttachmentId']
+                        )
+
+                    # Execute a SELECT statement to check
+                    # if the entry already exists
+                    search_query = "SELECT COUNT(*) " + \
+                        "FROM ChemAsso WHERE " + \
+                        "ID = ? AND AssociationType = ? " + \
+                        "AND BondType = ? " + \
+                        "AND Description = ? " + \
+                        "AND dataId = ?;"
+
+                    cursor.execute(search_query, ChemAsso_insert[:5])
+                    count = cursor.fetchone()[0]
+
+                    # Check the count to determine if the entry exists
+                    if count == 0:
+                        # Entry does not exist, proceed with insertion
+                        insert_query = "INSERT INTO ChemAsso (" + \
+                            "ID, " + \
+                            "AssociationType, " + \
+                            "BondType, " + \
+                            "Description, " + \
+                            "dataId, " + \
+                            "ComposingElementNameA, " + \
+                            "ComposingElementNameB, " + \
+                            "CompositiontypeB, " + \
+                            "CompositiontypeA, " + \
+                            "DomainElementNameB, " + \
+                            "DomainElementNameA, " + \
+                            "DomainAssociationId, " + \
+                            "ComposingElemetIdB, " + \
+                            "ComposingElemetIdA, " + \
+                            "ComposingElementTypeA, " + \
+                            "EntityDisplayNameB, " + \
+                            "ComposingElementTypeB, " + \
+                            "EntityDisplayNameA, " + \
+                            "AttachmentId) " + \
+                            "VALUES (?, ?, ?, ?, " + \
+                            "?, ?, ?, ?, ?, ?, ?, ?, " + \
+                            "?, ?, ?, ?, ?, ? , ?)"
+
+                        cursor.execute(
+                            insert_query,
+                            ChemAsso_insert
+                            )
+
+                        connection.commit()
+                    # else:
+                    #     # Entry already exists, skip
+                    #     print("Entry already exists, skipping...")
+            progress_bar.update(1)
+    cursor.close()

src/database_creation/data_utils.py

@@ -0,0 +1,207 @@
+import numpy as np
+import ast
+import csv
+import pickle
+import os
+import json
+
+
+def subset_and_unwrapp(
+    df,
+    subset_list,
+    target_column
+):
+
+    subset_df = df.loc[:, subset_list].copy()
+
+    subset_df[target_column] = subset_df[target_column].apply(
+        lambda x: ast.literal_eval(x) if isinstance(
+            x,
+            str
+        ) and x != 'nan' else np.nan)
+
+    subset_df = subset_df.explode(target_column)
+
+    subset_df = subset_df.reset_index(drop=True)
+
+    return subset_df
+
+
+def parse_overview_table(df_in):
+
+    columns = df_in.columns.to_list()
+
+    # Find columns that have string values representing lists
+    columns_with_lists = []
+    for column in df_in.columns:
+        if df_in[column].apply(
+            lambda x: isinstance(
+                x,
+                str
+                ) and x.startswith(
+                '['
+                ) and x.endswith(
+                ']')
+                ).any():
+
+            columns_with_lists.append(column)
+
+    overview_dict = {}
+    table_structure = ""
+
+    for column in columns[1:]:
+        if column in columns_with_lists:
+            temp_df = subset_and_unwrapp(
+                df_in,
+                [columns[0], column],
+                column
+            )
+
+        else:
+            temp_df = df_in[[columns[0], column]]
+
+        temp_key = "ID" + column
+
+        overview_dict[temp_key] = temp_df
+
+        table_text = "{table:" + temp_key + ","
+        column_text = "columns:[sampleId," + column + "]};"
+        entry = table_text + column_text
+        table_structure += entry
+
+    print(overview_dict.keys())
+
+    return overview_dict, table_structure
+
+
+def get_unique_value_list(sample_search_df,
+                          key,
+                          file_path,
+                          run=False):
+    if run:
+        com_list = sample_search_df[key].unique()
+        com_par_list = []
+        for item in com_list:
+            if item is not np.nan:
+                python_list = ast.literal_eval(item)
+                com_par_list.extend(python_list)
+            else:
+                com_par_list.append("NULL")
+
+        com_par_list = list(set(com_par_list))
+
+        if key in com_par_list:
+            com_par_list.remove(key)
+
+        # Save unique values to CSV
+        with open(file_path, 'w', newline='') as file:
+            writer = csv.writer(file)
+            writer.writerows([[value] for value in com_par_list])
+
+        print(f"Unique values for {key} saved to", file_path)
+        return com_par_list
+
+    else:
+        print(f"Skipeed for {key}")
+        com_par_list = []
+
+        with open(file_path, 'r') as file:
+            reader = csv.reader(file)
+            for row in reader:
+                com_par_list.append(row[0])
+
+        return com_par_list
+
+
+def extract_unique_options(
+        sample_search_df,
+        data_path,
+        run=False):
+
+    compo_file_path = data_path + "\\composition_list.csv"
+    compositions = get_unique_value_list(
+        sample_search_df,
+        'composition',
+        compo_file_path,
+        run=run)
+
+    functions_file_path = data_path + "\\functions_list.csv"
+    functions = get_unique_value_list(
+        sample_search_df,
+        'functions',
+        functions_file_path,
+        run=run)
+
+    characterizations_file_path = data_path + "\\characterizations_list.csv"
+    characterizations = get_unique_value_list(
+        sample_search_df,
+        'characterizations',
+        characterizations_file_path,
+        run=run)
+
+    return {
+        "compositions": compositions,
+        "functions": functions,
+        "characterizations": characterizations
+    }
+
+
+def load_sample_list(
+        output_data_dir,
+        read_sample,
+        n_to_read,
+        data_path
+        ):
+    sample_list_all_path = data_path + "\\sample_list_all.pickle"
+    Json_list = os.listdir(output_data_dir)
+    if read_sample:
+
+        sample_list = []
+        for i in range(0, n_to_read):
+            file_path = os.path.join(
+                output_data_dir,
+                Json_list[i])
+
+            with open(file_path, 'r') as file:
+                sample_list.append(json.load(file))
+
+        with open(sample_list_all_path, 'wb') as file:
+            pickle.dump(sample_list, file)
+    else:
+        with open(sample_list_all_path, 'rb') as file:
+            sample_list = pickle.load(file)
+
+    return sample_list
+
+
+def parse_dictionary(source_dictionary,
+                     key,
+                     new_dictionary):
+    for entry in source_dictionary:
+        new_dictionary[str(entry)] = source_dictionary[entry][key]
+
+
+def parse_overview_raw_data(
+        sample_search_df,
+        overview_data_path,
+        re_parse_overview=False
+        ):
+
+    overview_dict_path = overview_data_path + "\\overview_dict.pickle"
+    overview_table_path = overview_data_path + "\\overview_table.pickle"
+    if re_parse_overview:
+        overview_dict, table_structure = parse_overview_table(sample_search_df)
+
+        with open(overview_dict_path, 'wb') as file:
+            pickle.dump(overview_dict, file)
+
+        with open(overview_table_path, 'wb') as file:
+            pickle.dump(table_structure, file)
+    else:
+        with open(overview_dict_path, 'rb') as file:
+            overview_dict = pickle.load(file)
+
+        with open(overview_table_path, 'rb') as file:
+            table_structure = pickle.load(file)
+
+    return overview_dict, table_structure

src/database_creation/database_creation.py

@@ -0,0 +1,100 @@
+import data_utils as du
+import nanomaterial_entity_creation as nec
+import functionalizing_entity_creation as fec
+import chemical_association_creation as cac
+import general_info_creation as gic
+import publication_info_creation as pic
+import characterization_info_creation as cic
+import sqlite3
+
+
+def SQLdb_creation(
+    db_name,
+    sample_search_df,
+    overview_data_path,
+    sample_list,
+    connection,
+    re_parse=False
+):
+    """
+    Please note that this portion of the script is to
+    show how the database was created from the existing pulic
+    data download from caNanoLab and for the community
+    to inspect of any misconfiguration in the setup
+    of the backing database for the caNanoLibrarian App.
+    This is not intended to encourage public to ramp
+    downloading request to caNanoLab, please use the database
+    responsibly. Thank you.
+    """
+    table_names = []
+    table_schemas = []
+    resulting_schema_dict = {}
+
+    if re_parse:
+        overview_dict, table_structure = du.parse_overview_raw_data(
+            sample_search_df,
+            overview_data_path,
+            re_parse_overview=False
+            )
+
+        composition_dt = {}
+        characterization_dt = {}
+        publication_dt = {}
+        contact_dt = {}
+        for sample in sample_list:
+            sampleID = str(sample['sampleID'])
+            composition_dt[sampleID] = sample['composition']
+            characterization_dt[sampleID] = sample['characterization']
+            publication_dt[sampleID] = sample['publication']
+            contact_dt[sampleID] = sample['contact']
+
+        connection = sqlite3.connect(db_name)
+
+        print("Writing GeneralInfo...")
+        gic.create_general_info_tables(connection)
+        gic.general_info_to_sql(contact_dt, connection)
+
+        print("Writing NanoMaterialEntity...")
+        nec.create_nanomaterial_entity_tables(connection)
+        nec.nanomaterialentity_to_sql(composition_dt, connection)
+
+        print("Writing FunctionalizingEntity...")
+        fec.create_functionalizing_entity_tables(connection)
+        fec.functionalizingentity_to_sql(composition_dt, connection)
+
+        print("Writing ChemicalAssociation...")
+        cac.create_ChemAsso_tables(connection)
+        cac.chemicalassociation_to_sql(composition_dt, connection)
+
+        print("Writing Characteriztion...")
+        cic.create_characterization_dt_tables(connection)
+        cic.characterization_to_sql(characterization_dt, connection)
+
+        print("Writing Publication...")
+        pic.create_Publication_Info_tables(connection)
+        pic.publication_info_to_sql(publication_dt, connection)
+
+        print("Done!")
+    else:
+        cursor = connection.cursor()
+        # Get the list of tables in the database
+        cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
+        tables = cursor.fetchall()
+        # Print the schema of each table
+        for table in tables:
+            table_name = table[0]
+            table_names.append(table_name)
+            # print(f"Table: {table_name}")
+            # print("Schema:")
+            cursor.execute(f"PRAGMA table_info({table_name});")
+            schema = cursor.fetchall()
+            current_schema = []
+            for column in schema:
+                current_schema.append(f"{column[1]}: {column[2]}")
+            table_schemas.append(current_schema)
+            resulting_schema_dict[table_name] = current_schema
+
+        # Close the cursor and the database connection
+        cursor.close()
+
+    return resulting_schema_dict

src/database_creation/functionalizing_entity_creation.py

@@ -0,0 +1,146 @@
+import data_utils as du
+import sql_utils as su
+from tqdm.notebook import tqdm_notebook
+
+
+def create_functionalizing_entity_tables(connection):
+
+    FuncEntDes_str = "CREATE TABLE IF NOT EXISTS FuncEntDes " + \
+        "(ID INT, FunctionEntity VARCHAR(255), FunctionEntityType " + \
+        "VARCHAR(150), Description TEXT, ActivationMethod TEXT," + \
+        " pubChemID VARCHAR(50), MolarMass VARCHAR(100)," + \
+        " MolarMassUnit VARCHAR(100));"
+
+    FuncEntFunction_str = "CREATE TABLE IF NOT EXISTS FuncEntFunction " + \
+        "(ID INT, FunctionEntity VARCHAR(255), Function VARCHAR(255), " + \
+        "FunctionDescription TEXT);"
+
+    table_creation_querys = [
+        FuncEntDes_str,
+        FuncEntFunction_str
+    ]
+
+    for query in table_creation_querys:
+        results = su.simple_querry(
+            connection,
+            query
+            )
+        if len(results) == 0:
+            print("Table Exists")
+        else:
+            print(results)
+    su.show_tables(connection)
+
+
+def functionalizingentity_to_sql(
+        composition_dt,
+        connection
+):
+
+    functionalizingentity_dt = {}
+
+    du.parse_dictionary(
+        composition_dt,
+        "functionalizingentity",
+        functionalizingentity_dt
+        )
+
+    total_ids = len(functionalizingentity_dt)
+
+    with tqdm_notebook(
+        total=total_ids,
+        desc='Processing',
+        unit='ID'
+    ) as progress_bar:
+
+        for ID in functionalizingentity_dt:
+            sample_info = functionalizingentity_dt[ID]
+            for FuncEntity in sample_info:
+                FuncEntity_info = sample_info[FuncEntity]
+                for Entry in FuncEntity_info:
+                    # Create a cursor object
+                    cursor = connection.cursor()
+
+                    # Write to NanoEntDes
+                    FuncEntDes_insert = (
+                        ID,
+                        Entry['Name'],
+                        FuncEntity,
+                        Entry['description'],
+                        Entry['ActivationMethod'],
+                        Entry['pubChemID'],
+                        Entry['value'],
+                        Entry['valueUnit']
+                        )
+
+                    # Execute a SELECT statement to check
+                    # if the entry already exists
+
+                    search_query = "SELECT COUNT(*) FROM FuncEntDes" + \
+                        " WHERE ID = ? AND FunctionEntity = ?" + \
+                        " AND FunctionEntityType = ?" + \
+                        " AND Description = ?" + \
+                        " AND ActivationMethod = ?" + \
+                        " AND pubChemID = ?" + \
+                        " AND MolarMass = ?" + \
+                        " AND MolarMassUnit = ?;"
+
+                    cursor.execute(search_query, FuncEntDes_insert)
+                    count = cursor.fetchone()[0]
+
+                    # Check the count to determine if the entry exists
+                    if count == 0:
+                        # Entry does not exist, proceed with insertion
+                        insert_query = "INSERT INTO FuncEntDes " + \
+                                        "(ID, FunctionEntity, " + \
+                                        "FunctionEntityType, " + \
+                                        "Description, " + \
+                                        "ActivationMethod, pubChemID, " + \
+                                        "MolarMass, MolarMassUnit) " + \
+                                        "VALUES (?, ?, ?, ?, ?, ?, ?, ?)"
+                        cursor.execute(insert_query, FuncEntDes_insert)
+                        connection.commit()
+                    # else:
+                    #     # Entry already exists, skip
+                    #     print("Entry already exists, skipping...")
+
+                    # Commit the changes
+                    connection.commit()
+
+                    for function in Entry['Functions']:
+
+                        # Write to NanoEntCom
+                        FuncEntFunction_insert = (
+                            ID,
+                            Entry['Name'],
+                            function['Type'],
+                            function['FunctionDescription']
+                            )
+
+                        # Execute a SELECT statement to check
+                        # if the entry already exists
+                        search_query = "SELECT COUNT(*) " + \
+                            "FROM FuncEntFunction WHERE " + \
+                            "ID = ? AND FunctionEntity = ? " + \
+                            "AND Function = ? " + \
+                            "AND FunctionDescription = ?;"
+
+                        cursor.execute(search_query, FuncEntFunction_insert)
+                        count = cursor.fetchone()[0]
+
+                        # Check the count to determine if the entry exists
+                        if count == 0:
+                            # Entry does not exist, proceed with insertion
+                            insert_query = "INSERT INTO FuncEntFunction " + \
+                                            "(ID, FunctionEntity, " + \
+                                            "Function, " + \
+                                            "FunctionDescription) " + \
+                                            "VALUES (?, ?, ?, ?)"
+                            cursor.execute(insert_query,
+                                           FuncEntFunction_insert)
+                            connection.commit()
+                        # else:
+                        #     # Entry already exists, skip
+                        #     print("Entry already exists, skipping...")
+            progress_bar.update(1)
+    cursor.close()

src/database_creation/general_info_creation.py

@@ -0,0 +1,135 @@
+import sql_utils as su
+from tqdm.notebook import tqdm_notebook
+import datetime
+
+
+def create_general_info_tables(connection):
+
+    general_info_string = "CREATE TABLE IF NOT EXISTS GeneralInfo " + \
+            "(ID INT, sampleName VARCHAR(150), " + \
+            "createdYear INT, createdMonth INT);"
+
+    keyword_info_string = "CREATE TABLE IF NOT EXISTS " + \
+        "SampleKeyWords (ID INT, sampleName VARCHAR(150), " + \
+        "SampleKeyWord VARCHAR(150));"
+
+    table_creation_querys = [
+        general_info_string,
+        keyword_info_string
+        ]
+
+    for query in table_creation_querys:
+        results = su.simple_querry(
+            connection,
+            query
+            )
+        if len(results) == 0:
+            print("Table Exists")
+        else:
+            print(results)
+    su.show_tables(connection)
+
+
+def general_info_to_sql(
+        contact_dt,
+        connection
+):
+
+    total_ids = len(contact_dt)
+
+    with tqdm_notebook(
+        total=total_ids,
+        desc='Processing',
+        unit='ID'
+    ) as progress_bar:
+
+        # Create a cursor object
+        cursor = connection.cursor()
+
+        for ID in contact_dt:
+            sample_info = contact_dt[ID]
+
+            datetime_obj = datetime.datetime.fromtimestamp(
+                sample_info['createdDate'] / 1000
+                )
+
+            year = datetime_obj.year
+            month = datetime_obj.month
+
+            # Write to NanoEntCom
+            GeneralInfo_insert = (
+                ID,
+                sample_info['sampleName'],
+                year,
+                month
+                )
+
+            # Execute a SELECT statement to check
+            # if the entry already exists
+            search_query = "SELECT COUNT(*) " + \
+                "FROM GeneralInfo WHERE " + \
+                "ID = ? AND sampleName = ? " + \
+                "AND createdYear = ? AND createdMonth = ?;"
+
+            cursor.execute(search_query, GeneralInfo_insert)
+            count = cursor.fetchone()[0]
+
+            # Check the count to determine if the entry exists
+            if count == 0:
+                # Entry does not exist, proceed with insertion
+                insert_query = "INSERT INTO GeneralInfo (" + \
+                    "ID, " + \
+                    "sampleName, " + \
+                    "createdYear, " + \
+                    "createdMonth) " + \
+                    "VALUES (?, ?, ?, ?)"
+
+                cursor.execute(
+                    insert_query,
+                    GeneralInfo_insert
+                    )
+
+                connection.commit()
+
+            if sample_info['keywords'] and '<br />' in sample_info['keywords']:
+                keyword_list = sample_info['keywords'].split("<br />")
+            else:
+                if sample_info['keywords']:
+                    keyword_list = [sample_info['keywords']]
+                else:
+                    keyword_list = ["None"]
+
+            for keyword in keyword_list:
+                # Write to NanoEntCom
+                keyword_insert = (
+                    ID,
+                    sample_info['sampleName'],
+                    keyword
+                    )
+
+                # Execute a SELECT statement to check
+                # if the entry already exists
+                search_query = "SELECT COUNT(*) " + \
+                    "FROM SampleKeyWords WHERE " + \
+                    "ID = ? AND sampleName = ? " + \
+                    "AND SampleKeyWord = ?;"
+
+                cursor.execute(search_query, keyword_insert)
+                count = cursor.fetchone()[0]
+
+                # Check the count to determine if the entry exists
+                if count == 0:
+                    # Entry does not exist, proceed with insertion
+                    insert_query = "INSERT INTO SampleKeyWords (" + \
+                        "ID, " + \
+                        "sampleName, " + \
+                        "SampleKeyWord) " + \
+                        "VALUES (?, ?, ?)"
+
+                    cursor.execute(
+                        insert_query,
+                        keyword_insert
+                        )
+
+            progress_bar.update(1)
+    cursor.close()

src/database_creation/nanomaterial_entity_creation.py

@@ -0,0 +1,175 @@
+import data_utils as du
+import sql_utils as su
+from tqdm.notebook import tqdm_notebook
+
+
+def create_nanomaterial_entity_tables(connection):
+
+    NanoEntDes_str = "CREATE TABLE IF NOT EXISTS `NanoEntDes` " + \
+        "(`ID` INT, `NanoEntity` VARCHAR(255), `Description` TEXT);"
+
+    NanoEntCom_str = "CREATE TABLE IF NOT EXISTS NanoEntCom " + \
+        "(ID INT, NanoEntity VARCHAR(255), Composition VARCHAR(100), " + \
+        "CompositionType VARCHAR(100), MolecularWeight VARCHAR(150), " + \
+        "PubChemID VARCHAR(255));"
+
+    table_creation_querys = [
+        NanoEntDes_str,
+        NanoEntCom_str
+        ]
+
+    for query in table_creation_querys:
+        results = su.simple_querry(
+            connection,
+            query
+            )
+        if len(results) == 0:
+            print("Table Exists")
+        else:
+            print(results)
+    su.show_tables(connection)
+
+
+def nanomaterialentity_to_sql(
+        composition_dt,
+        connection
+):
+
+    nanomaterialentity_dt = {}
+
+    du.parse_dictionary(
+        composition_dt,
+        "nanomaterialentity",
+        nanomaterialentity_dt
+        )
+
+    total_ids = len(nanomaterialentity_dt)
+
+    with tqdm_notebook(
+        total=total_ids,
+        desc='Processing',
+        unit='ID'
+    ) as progress_bar:
+
+        for ID in nanomaterialentity_dt:
+            sample_info = nanomaterialentity_dt[ID]
+            for NanoEntity in sample_info:
+                NanoEntity_info = sample_info[NanoEntity]
+                for Entry in NanoEntity_info:
+                    # Create a cursor object
+                    cursor = connection.cursor()
+
+                    # Write to NanoEntDes
+                    NanoEntDes_insert = (ID, NanoEntity, Entry['Description'])
+
+                    # Execute a SELECT statement to check
+                    # if the entry already exists
+
+                    search_query = "SELECT COUNT(*) FROM NanoEntDes" + \
+                        " WHERE ID = ? AND NanoEntity = ?" + \
+                        " AND Description = ?"
+
+                    cursor.execute(search_query, NanoEntDes_insert)
+                    count = cursor.fetchone()[0]
+
+                    # Check the count to determine if the entry exists
+                    if count == 0:
+                        # Entry does not exist, proceed with insertion
+                        insert_query = "INSERT INTO NanoEntDes " + \
+                                        "(ID, NanoEntity, Description) " + \
+                                        "VALUES (?, ?, ?)"
+                        cursor.execute(insert_query, NanoEntDes_insert)
+                        connection.commit()
+                    # else:
+                    #     # Entry already exists, skip
+                    #     print("Entry already exists, skipping...")
+
+                    # Commit the changes
+                    connection.commit()
+
+                    for composition in Entry['ComposingElements']:
+                        if 'DisplayName' in composition and not composition[
+                            'DisplayName'
+                        ]:
+
+                            composition_type = "NULL"
+                            composition_name = "NULL"
+                            composition_MolecularWeight = "NULL"
+
+                        else:
+                            # Extract composition_type
+                            displayname = composition['DisplayName']
+                            index_open = displayname.find("(")
+                            composition_type = displayname[
+                                :index_open
+                                ].strip() if index_open != -1 else "NULL"
+
+                            # Extract composition_name and composition_quantity
+                            index_name = displayname.find(
+                                "name: "
+                            ) + len("name: ")
+                            index_amount = displayname.find(", amount: ")
+
+                            if index_name != -1:
+                                if index_amount != -1:
+                                    composition_name = displayname[
+                                        index_name:index_amount
+                                        ].strip()
+                                    composition_MolecularWeight = displayname[
+                                        index_amount + len(", amount: "):-1
+                                        ].strip()
+                                else:
+                                    composition_name = displayname[
+                                        index_name:-1
+                                        ].strip()
+                                    composition_MolecularWeight = "NULL"
+                            else:
+                                composition_name = "NULL"
+                                composition_MolecularWeight = "NULL"
+
+                        if 'PubChemId' in composition and not composition[
+                            'PubChemId'
+                        ]:
+                            PubChemID = "Null"
+                        else:
+                            PubChemID = composition['PubChemId']
+
+                    # Write to NanoEntCom
+                        NanoEntCom_insert = (
+                            ID,
+                            NanoEntity,
+                            composition_name,
+                            composition_type,
+                            composition_MolecularWeight,
+                            PubChemID
+                            )
+
+                        # Execute a SELECT statement to check
+                        # if the entry already exists
+                        search_query = "SELECT COUNT(*) " + \
+                            "FROM NanoEntCom WHERE " + \
+                            "ID = ? AND NanoEntity = ? " + \
+                            "AND Composition = ? " + \
+                            "AND CompositionType = ? " + \
+                            "AND MolecularWeight = ? " + \
+                            "AND PubChemID = ?"
+
+                        cursor.execute(search_query, NanoEntCom_insert)
+                        count = cursor.fetchone()[0]
+
+                        # Check the count to determine if the entry exists
+                        if count == 0:
+                            # Entry does not exist, proceed with insertion
+                            insert_query = "INSERT INTO NanoEntCom " + \
+                                            "(ID, NanoEntity, " + \
+                                            "Composition, " + \
+                                            "CompositionType, " + \
+                                            "MolecularWeight, PubChemID) " + \
+                                            "VALUES (?, ?, ?, ?, ?, ?)"
+                            cursor.execute(insert_query, NanoEntCom_insert)
+                            connection.commit()
+                        # else:
+                        #     # Entry already exists, skip
+                        #     print("Entry already exists, skipping...")
+            progress_bar.update(1)
+    cursor.close()

src/database_creation/publication_info_creation.py

@@ -0,0 +1,202 @@
+import sql_utils as su
+from tqdm.notebook import tqdm_notebook
+import re
+
+
+def create_Publication_Info_tables(connection):
+
+    general_info_string = "CREATE TABLE IF NOT EXISTS PublicationInfo " + \
+            "(ID INT, PMID INT, year INT, " + \
+            "title TEXT, author TEXT, journal TEXT, " + \
+            "publicationCategories TEXT, description TEXT);"
+
+    keyword_info_string = "CREATE TABLE IF NOT EXISTS " + \
+        "PublicationKeyWords (ID INT, PublicationKeyWord VARCHAR(150));"
+
+    table_creation_querys = [
+        general_info_string,
+        keyword_info_string
+        ]
+
+    for query in table_creation_querys:
+        results = su.simple_querry(
+            connection,
+            query
+            )
+        if len(results) == 0:
+            print("Table Exists")
+        else:
+            print(results)
+
+    su.show_tables(connection)
+
+
+def publication_info_to_sql(
+        publication_dt,
+        connection
+):
+
+    total_ids = len(publication_dt)
+
+    def extract_information(string):
+        pattern = r"(.*?)\.\s*(\d{4});.*?PMID:\s*(\d+)"
+        match = re.search(pattern, string)
+
+        if match:
+            publication = match.group(1).strip()
+            year = match.group(2).strip()
+            pmid = match.group(3)
+
+            pub_list = publication.split(".")
+            if len(pub_list) <= 2:
+                if "," not in pub_list[0]:
+                    year_match = re.search(r'\b(\d{4})\b', string)
+                    year = year_match.group(1)
+
+                    # Extracting the journal name
+                    journal_match = re.search(r'\. (.+?)\.', string)
+                    journal = journal_match.group(1)
+
+                    # Extracting the PMID
+                    pmid_match = re.search(r'PMID: (\d+)', string)
+                    pmid = pmid_match.group(1)
+
+                    title_match = re.search(r'^([^\.]+)\.', string)
+                    title = title_match.group(1).strip()
+
+                    return {
+                        'journal': journal,
+                        'pmid': pmid,
+                        'year': year,
+                        'title': title,
+                        'author': "None"
+                    }
+                else:
+                    print(pub_list)
+            else:
+                return {
+                    'journal': pub_list[2].strip(),
+                    'pmid': pmid,
+                    'year': year,
+                    'title': pub_list[1].strip(),
+                    'author': pub_list[0].strip()
+                    }
+
+        return {
+            'journal': "None",
+            'pmid': "None",
+            'year': "None",
+            'title': "None",
+            'author': "None"
+            }
+
+    with tqdm_notebook(
+        total=total_ids,
+        desc='Processing',
+        unit='ID'
+    ) as progress_bar:
+
+        # Create a cursor object
+        cursor = connection.cursor()
+
+        for ID in publication_dt:
+            sample_info = publication_dt[ID]
+
+            for category in sample_info['category2Publications']:
+                info_dict = sample_info['category2Publications'][category]
+                for info in info_dict:
+
+                    citation_string = info['displayName']
+
+                    article_info = extract_information(citation_string)
+
+                    # Write to NanoEntCom
+                    publication_insert = (
+                        ID,
+                        article_info['pmid'],
+                        article_info['year'],
+                        article_info['title'],
+                        article_info['author'],
+                        article_info['journal'],
+                        category,
+                        info['description']
+                        )
+
+                    # Execute a SELECT statement to check
+                    # if the entry already exists
+                    search_query = "SELECT COUNT(*) " + \
+                        "FROM PublicationInfo  WHERE " + \
+                        "ID = ? AND PMID  = ? AND year  = ? AND " + \
+                        "title  = ? AND author  = ? AND journal  = ? AND " + \
+                        "publicationCategories  = ? AND description  = ?;"
+
+                    cursor.execute(search_query, publication_insert)
+                    count = cursor.fetchone()[0]
+
+                    # Check the count to determine if the entry exists
+                    if count == 0:
+                        # Entry does not exist, proceed with insertion
+                        insert_query = "INSERT INTO PublicationInfo (" + \
+                            "ID, " + \
+                            "PMID, " + \
+                            "year, " + \
+                            "title, " + \
+                            "author, " + \
+                            "journal, " + \
+                            "publicationCategories, " + \
+                            "description) " + \
+                            "VALUES (?, ?, ?, ?, ?, ?, ?, ?)"
+
+                        cursor.execute(
+                            insert_query,
+                            publication_insert
+                            )
+
+                        connection.commit()
+
+                    if info[
+                            'keywordsDisplayName'
+                        ] and '<br />' in info[
+                            'keywordsDisplayName'
+                    ]:
+                        keyword_list = info[
+                            'keywordsDisplayName'
+                            ].split("<br />")
+                    else:
+                        if info['keywordsDisplayName']:
+                            keyword_list = [info['keywordsDisplayName']]
+                        else:
+                            keyword_list = ["None"]
+
+                    for keyword in keyword_list:
+                        # Write to NanoEntCom
+                        keyword_insert = (
+                            ID,
+                            keyword
+                            )
+
+                        # Execute a SELECT statement to check
+                        # if the entry already exists
+                        search_query = "SELECT COUNT(*) " + \
+                            "FROM PublicationKeyWords WHERE " + \
+                            "ID = ? AND PublicationKeyWord  = ?;"
+
+                        cursor.execute(search_query, keyword_insert)
+                        count = cursor.fetchone()[0]
+
+                        # Check the count to determine if the entry exists
+                        if count == 0:
+                            # Entry does not exist, proceed with insertion
+                            insert_query = "INSERT INTO " + \
+                                "PublicationKeyWords (" + \
+                                "ID, " + \
+                                "PublicationKeyWord ) " + \
+                                "VALUES (?, ?)"
+
+                            cursor.execute(
+                                insert_query,
+                                keyword_insert
+                                )
+
+            progress_bar.update(1)
+    cursor.close()

templates/index.html

@@ -0,0 +1,252 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>caNanoWiki AI</title>
+    <style>
+        body {
+            font-family: Arial, sans-serif;
+            background-color: #001f3f;  /* Dark blue */
+            color: #fff;
+            margin: 0;
+            padding: 20px;
+        }
+
+        h1 {
+            font-size: 32px;
+            text-align: center;
+            margin-bottom: 40px;
+        }
+
+        .logo {
+            display: block;
+            margin: 0 auto;
+            margin-bottom: 40px;
+            width: 200px;
+        }
+
+        form {
+            text-align: center;
+            margin-bottom: 40px;
+        }
+
+        label {
+            display: block;
+            font-size: 20px;
+            margin-bottom: 10px;
+        }
+
+        input[type="text"] {
+            font-size: 18px;
+            padding: 10px;
+            width: 500px;
+            border-radius: 10px;
+        }
+
+        button {
+            font-size: 18px;
+            padding: 10px 20px;
+            background-color: #00bfff;
+            color: #fff;
+            border: none;
+            border-radius: 10px;
+            cursor: pointer;
+            margin-top: 10px;
+        }
+
+        button:hover {
+            background-color: #0088cc;
+        }
+
+        .result {
+            background-color: #fff;
+            color: #000;
+            padding: 20px;
+            border-radius: 10px;
+            text-align: center;
+            box-shadow: 0 2px 4px rgba(0, 0, 0, 0.2);
+            margin: 0 auto;
+            max-width: 800px;
+            overflow-y: auto;  /* Enable vertical scrollbar */
+            max-height: 480px;  /* Set maximum height for the result window */
+        }
+
+        .export-button {
+            font-size: 18px;
+            padding: 10px 20px;
+            background-color: #008000;  /* Green */
+            color: #fff;
+            border: none;
+            border-radius: 10px;
+            cursor: pointer;
+            margin-top: 10px;
+        }
+
+        .export-button:hover {
+            background-color: #006400;  /* Dark green */
+        }   
+
+        .loading {
+            font-size: 18px;
+            text-align: center;
+            margin-bottom: 20px;
+        }
+
+        .another-box.folded {
+            display: flex;
+            justify-content: center;
+            align-items: center;
+            background-color: #999;
+            color: #fff;
+            border-radius: 10px;
+            padding: 20px;
+            cursor: pointer;
+            /* Additional styling for the folded state */
+        }
+
+        .another-box {
+            background-color: #fff;
+            color: #000;
+            border-radius: 10px;
+            padding: 20px;
+            box-shadow: 0 2px 4px rgba(0, 0, 0, 0.2);
+            margin-top: 20px;
+            /* Additional styling for the unfolded state */
+        }
+
+        .dataframe {
+            border-collapse: collapse;
+            width: 100%;
+        }
+
+        .dataframe th,
+        .dataframe td {
+            border: 1px solid #ddd;
+            padding: 8px;
+            text-align: left;
+        }
+
+        .dataframe th {
+            background-color: #f2f2f2;
+            font-weight: bold;
+        }
+
+        .form-buttons {
+            display: flex;
+            justify-content: space-between;
+            align-items: center;
+        }
+
+        .form-buttons button {
+            margin: 10px;
+        }
+    </style>
+</head>
+<body>
+    <h1>Welcome to caNanoLibrarian!</h1>
+
+    <img src="{{ url_for('static', filename='caNanoLablogo.jpg') }}" alt="caNanoWiki AI Logo" class="logo">
+
+
+    <form method="POST" action="/">
+        <label for="user_input">How can I help?</label>
+        <input type="text" id="user_input" name="user_input" value="{{ user_input }}" autofocus>
+        <br>
+        <button type="submit">Search</button>
+        <button onclick="openPopup()">Database Structure</button>
+    </form>
+
+    {% if processing %}
+        <p class="loading">Working on it...</p>
+    {% endif %}
+
+    {% if processed_input %}
+        <div class="result">
+            <p>{{ processed_input | safe }}</p>
+        </div>
+        <button class="export-button" onclick="exportToCSV()">Export as CSV</button>
+        <div class="Source-Info" onclick="toggleFoldedState(this)">
+            <h2>SQL Query String</h2>
+            <p>{{ source_sections | nl2br | safe }}</p>
+        </div>
+    {% else %}
+        <div class="result" style="display: none;"></div>
+    {% endif %}
+
+<script>
+    function toggleFoldedState(element) {
+        element.classList.toggle('folded');
+    }
+
+    function exportToCSV() {
+    // Get the HTML table element containing the DataFrame
+    var table = document.querySelector('.result table');
+
+    // Create an empty string to store the CSV content
+    var csvContent = "";
+
+    // Iterate through each row in the table
+    for (var i = 0; i < table.rows.length; i++) {
+        var row = table.rows[i];
+
+        // Iterate through each cell in the row
+        for (var j = 0; j < row.cells.length; j++) {
+            var cell = row.cells[j];
+
+            // Extract the cell value and add it to the CSV content
+            var cellValue = cell.innerText.trim();
+            csvContent += '"' + cellValue + '",';
+        }
+
+        // Add a line break after each row
+        csvContent += '\n';
+    }
+
+    // Create a temporary link element
+    var link = document.createElement('a');
+    link.setAttribute('href', 'data:text/csv;charset=utf-8,' + encodeURIComponent(csvContent));
+    link.setAttribute('download', 'result.csv');
+    link.style.display = 'none';
+
+    // Add the link to the document and simulate a click event to trigger the download
+    document.body.appendChild(link);
+    link.click();
+    document.body.removeChild(link);
+    }
+
+    function openPopup() {
+            var popupWindow = window.open("", "Popup Window", "width=400,height=500");
+            var content = `
+                <html>
+                <head>
+                    <title>Pop-up Window</title>
+                </head>
+                <body>
+                    <h2>Database Structure</h2>
+                    <p>{table:NanoEntDes,attributes:[ID(Primary),NanoEntity,Description]}</p>
+                    <p>{table:NanoEntCom,attributes:[ID(Primary),NanoEntity,Composition,CompositionType,MolecularWeight,PubChemID]}</p>
+                    <p>{table:FuncEntDes,attributes:[ID(Primary),FunctionEntity,FunctionEntityType,Description,ActivationMethod,pubChemID,MolarMass,MolarMassUnit]}</p>
+                    <p>{table:FuncEntFunction,attributes:[ID(Primary),FunctionEntiry,Function,FunctionDescription]}</p>
+                    <p>{table:ChemAsso,attributes:[ID(Primary),AssociationType,BondType,Description,dataId,ComposingElementNameA,<br>
+                    ComposingElementNameB,CompositiontypeB,CompositiontypeA,DomainElementNameB,DomainElementNameA,DomainAssociationId,<br>
+                    ComposingElemetIdB,ComposingElemetIdA,ComposingElementTypeA,EntityDisplayNameB,ComposingElementTypeB,EntityDisplayNameA,AttachmentId]}</p>
+                    <p>{table:GeneralInfo,attributes:[ID(Primary),sampleName,createdYear,createdMonth]}</p>
+                    <p>{table:SampleKeyWords,attributes:[ID(Primary),sampleName,SampleKeyWord]}</p>
+                    <p>{table:PublicationInfo,attributes:[ID(Primary),PMID,year,title,author,journal,publicationCategories,description]}</p>
+                    <p>{table:PublicationKeyWords,attributes:[ID(Primary),sampleName,SampleKeyWord]}</p>
+                    <p>{table:CharacterizationInfo,attributes:[ID(Primary),CharType,CharName,AssayType,Protocol,DesignDescription,AnalysisAndConclusion]}</p>
+                    <p>{table:CharExpConfig,attributes:[ID(Primary),CharType,CharName,AssayType,ExpConfigTechnique,ExpConfigInstruments,ExpConfigDescription]}</p>
+                    <p>{table:CharResultDescriptions,attributes:[ID(Primary),CharType,CharName,AssayType,CharResultDescription]}</p>
+                    <p>{table:CharResultKeywords,attributes:[ID(Primary),CharType,CharName,AssayType,CharResultKeyword]}</p>
+                    <p>{table:CharResultTables,attributes:[ID(Primary),CharType,CharName,AssayType,CharTable]}</p>
+                </body>
+                </html>
+            `;
+
+            var popupWindow = window.open("", "Popup Window", "width=600,height=400");
+            popupWindow.document.write(content);
+            popupWindow.document.close();
+        }
+</script>
+</body>
+</html>
+

templates/login.html

@@ -0,0 +1,60 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Login</title>
+    <style>
+        body {
+            background-color: #11182B;
+            font-family: Arial, sans-serif;
+            color: #FFFFFF;
+            display: flex;
+            align-items: center;
+            justify-content: center;
+            height: 100vh;
+        }
+        
+        .login-container {
+            width: 350px;
+            padding: 20px;
+            background-color: #223E6D;
+            border-radius: 10px;
+        }
+
+        .login-container label, .login-container input {
+            display: block;
+            width: 90%;
+            margin-bottom: 10px;
+        }
+
+        .login-container input {
+            padding: 10px;
+            border-radius: 5px;
+        }
+
+        .login-container button {
+            display: block;
+            width: 100%;
+            padding: 10px;
+            border: none;
+            border-radius: 5px;
+            background-color: #2D82B7;
+            color: #FFFFFF;
+            cursor: pointer;
+        }
+
+        .login-container button:hover {
+            background-color: #1B577B;
+        }
+    </style>
+</head>
+<body>
+    <div class="login-container">
+        <h1>Login</h1>
+        <form method="POST" action="/login">
+            <label for="passcode">Please enter the passcode:</label>
+            <input type="password" id="passcode" name="passcode">
+            <button type="submit">Submit</button>
+        </form>
+    </div>
+</body>
+</html>