Migrate from replicate to together.ai

.gitignore

@@ -0,0 +1,21 @@
+.venv/
+.env
+
+var/
+lib/
+Scripts/
+include/
+
+*.pyc
+__pycache__/
+
+instance/
+
+.pytest_cache/
+.coverage
+htmlcov/
+
+dist/
+build/
+*.egg-info/
+test.py

app.py

@@ -1,16 +1,11 @@
-from supabase import create_client
-from supabase.lib.client_options import ClientOptions
 from sentence_transformers import SentenceTransformer
-import replicate
+from together import Together
+from dotenv import load_dotenv
 import vecs
 import os
 import gradio as gr
 
-
-key = os.getenv("Key")
-url = os.getenv("url")
-opts = ClientOptions().replace(schema="vecs")
-client = create_client(url, key, options=opts)
+load_dotenv()
 
 user = os.getenv("user")
 password = os.getenv("password")
@@ -20,55 +15,15 @@ db_name = "postgres"
 DB_CONNECTION = f"postgresql://{user}:{password}@{host}:{port}/{db_name}"
 vx = vecs.create_client(DB_CONNECTION)
 model = SentenceTransformer('Snowflake/snowflake-arctic-embed-xs')
+client = Together(api_key=os.getenv('TOGETHER_API_KEY'))
 
-def find_prediction(prediction_list, id):
-  for item in prediction_list:
-    temp_dict = dict(item)
-    if temp_dict.get("id") == id:
-      return temp_dict
-
-def find_id(prediction_list, inp):
-  id = ""
-  for item in prediction_list:
-    temp_dict = dict(item)
-    if temp_dict.get("input").get("prompt") == inp:
-      id = temp_dict.get("id")
-      break
-    else:
-      pass
-  return id
-
-def live_inference(prompt, max_new_tokens = 1024, top_k = 50, top_p = 0.9, temperature = 0.6, presence_penalty=1.15):
-  output = replicate.run(
-      "meta/meta-llama-3-8b-instruct",
-      input={
-          "top_k": top_k,
-          "top_p": top_p,
-          "prompt": prompt,
-          "temperature": temperature,
-          "max_new_tokens": max_new_tokens,
-          "prompt_template": "{prompt}",
-          "frequency_penalty": presence_penalty,
-          "seed": 61001
-      })
-
-  id = find_id(replicate.predictions.list(), prompt)
-  generating = True
-  out = ""
-  while generating:
-    prediction_list = replicate.predictions.list()
-    prediction = find_prediction(prediction_list, id)
-    try:
-      if prediction.get("status") != "succeeded":
-          pass
-      else:
-        for item in prediction.get("output"):
-          out += item
-        generating = False
-    except:
-      pass
-  return out
-
+def live_inference(messages, max_new_tokens = 512):
+    response = client.chat.completions.create(
+    model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+    messages = messages,
+    max_tokens = max_new_tokens
+    )
+    return response.choices[0].message.content
 
 def query_db(query, limit = 5, filters = {}, measure = "cosine_distance", include_value = False, include_metadata=False, table = "2023"):
   query_embeds = vx.get_or_create_collection(name= table, dimension=384)
@@ -105,27 +60,24 @@ def referencias(results):
   return references
 
 def inference(prompt):
-  encoded_prompt = model.encode(prompt)
-  years = range(2020, 2025)
+  encoded_prompt1 = model.encode(prompt)
+  years = range(2019, 2025)
   results = []
   for year in years:
-    results.extend(query_db(encoded_prompt, include_metadata = True, table = str(year), include_value=True, limit = 3))
+    results.extend(query_db(encoded_prompt1, include_metadata = True, table = str(year), include_value=True, limit = 5))
   results.sort(key=sort_by_score, reverse=True)
-  context =f"""
-  <|begin_of_text|>
-  <|start_header_id|>system<|end_header_id|>
-  Eres Ticio, un asistente de investigación jurídica. Tu deber es organizar el contenido de las sentencias de la jurisprudencia de acuerdo 
-  a las necesidades del usuario. Debes responder solo en español. Debes responder solo en base a la información del contexto a continuación.
-  Siempre debes mencionar la fuente en tu escrito, debe tener un estilo formal y juridico.
-  Contexto: 
-  {construct_result(results)}
-  <|eot_id|>
-  <|start_header_id|>user<|end_header_id|>
-  {prompt}
-  <|eot_id|>
-  <|start_header_id|>assistant<|end_header_id|>
-  """
-  return live_inference(context, max_new_tokens=512) + '\n' + referencias(results)
+  researchAI=[
+        {"role": "system", "content": f"""
+                  Eres Ticio, un asistente de investigación jurídica. Tu deber es organizar el contenido de las sentencias de la jurisprudencia de acuerdo 
+                  a las necesidades del usuario. Debes responder solo en español. Debes responder solo en base a la información del contexto a continuación.
+                  Siempre debes mencionar la fuente en tu escrito, debe tener un estilo formal y juridico.
+                  Contexto: 
+                  {construct_result(results)}
+                  """
+        },
+        {"role": "user", "content": prompt},
+    ]
+  return live_inference(researchAI, max_new_tokens=1024) + '\n' + referencias(results)
 
 theme = gr.themes.Base(
     primary_hue="red",

pyvenv.cfg

@@ -0,0 +1,5 @@
+home = C:\Users\jacob\AppData\Local\Programs\Python\Python312
+include-system-site-packages = false
+version = 3.12.3
+executable = C:\Users\jacob\AppData\Local\Programs\Python\Python312\python.exe
+command = C:\Users\jacob\AppData\Local\Programs\Python\Python312\python.exe -m venv C:\Users\jacob\CorteConstitucional

requirements.txt

@@ -1,4 +1,5 @@
 vecs
-replicate
+together
 supabase
 sentence-transformers
+python-dotenv

share/man/man1/isympy.1

@@ -0,0 +1,188 @@
+'\" -*- coding: us-ascii -*-
+.if \n(.g .ds T< \\FC
+.if \n(.g .ds T> \\F[\n[.fam]]
+.de URL
+\\$2 \(la\\$1\(ra\\$3
+..
+.if \n(.g .mso www.tmac
+.TH isympy 1 2007-10-8 "" ""
+.SH NAME
+isympy \- interactive shell for SymPy
+.SH SYNOPSIS
+'nh
+.fi
+.ad l
+\fBisympy\fR \kx
+.if (\nx>(\n(.l/2)) .nr x (\n(.l/5)
+'in \n(.iu+\nxu
+[\fB-c\fR | \fB--console\fR] [\fB-p\fR ENCODING | \fB--pretty\fR ENCODING] [\fB-t\fR TYPE | \fB--types\fR TYPE] [\fB-o\fR ORDER | \fB--order\fR ORDER] [\fB-q\fR | \fB--quiet\fR] [\fB-d\fR | \fB--doctest\fR] [\fB-C\fR | \fB--no-cache\fR] [\fB-a\fR | \fB--auto\fR] [\fB-D\fR | \fB--debug\fR] [
+-- | PYTHONOPTIONS]
+'in \n(.iu-\nxu
+.ad b
+'hy
+'nh
+.fi
+.ad l
+\fBisympy\fR \kx
+.if (\nx>(\n(.l/2)) .nr x (\n(.l/5)
+'in \n(.iu+\nxu
+[
+{\fB-h\fR | \fB--help\fR}
+|
+{\fB-v\fR | \fB--version\fR}
+]
+'in \n(.iu-\nxu
+.ad b
+'hy
+.SH DESCRIPTION
+isympy is a Python shell for SymPy. It is just a normal python shell
+(ipython shell if you have the ipython package installed) that executes
+the following commands so that you don't have to:
+.PP
+.nf
+\*(T<
+>>> from __future__ import division
+>>> from sympy import *
+>>> x, y, z = symbols("x,y,z")
+>>> k, m, n = symbols("k,m,n", integer=True)
+    \*(T>
+.fi
+.PP
+So starting isympy is equivalent to starting python (or ipython) and
+executing the above commands by hand. It is intended for easy and quick
+experimentation with SymPy. For more complicated programs, it is recommended
+to write a script and import things explicitly (using the "from sympy
+import sin, log, Symbol, ..." idiom).
+.SH OPTIONS
+.TP
+\*(T<\fB\-c \fR\*(T>\fISHELL\fR, \*(T<\fB\-\-console=\fR\*(T>\fISHELL\fR
+Use the specified shell (python or ipython) as
+console backend instead of the default one (ipython
+if present or python otherwise).
+
+Example: isympy -c python
+
+\fISHELL\fR could be either
+\&'ipython' or 'python'
+.TP
+\*(T<\fB\-p \fR\*(T>\fIENCODING\fR, \*(T<\fB\-\-pretty=\fR\*(T>\fIENCODING\fR
+Setup pretty printing in SymPy. By default, the most pretty, unicode
+printing is enabled (if the terminal supports it). You can use less
+pretty ASCII printing instead or no pretty printing at all.
+
+Example: isympy -p no
+
+\fIENCODING\fR must be one of 'unicode',
+\&'ascii' or 'no'.
+.TP
+\*(T<\fB\-t \fR\*(T>\fITYPE\fR, \*(T<\fB\-\-types=\fR\*(T>\fITYPE\fR
+Setup the ground types for the polys. By default, gmpy ground types
+are used if gmpy2 or gmpy is installed, otherwise it falls back to python
+ground types, which are a little bit slower. You can manually
+choose python ground types even if gmpy is installed (e.g., for testing purposes).
+
+Note that sympy ground types are not supported, and should be used
+only for experimental purposes.
+
+Note that the gmpy1 ground type is primarily intended for testing; it the
+use of gmpy even if gmpy2 is available.
+
+This is the same as setting the environment variable
+SYMPY_GROUND_TYPES to the given ground type (e.g.,
+SYMPY_GROUND_TYPES='gmpy')
+
+The ground types can be determined interactively from the variable
+sympy.polys.domains.GROUND_TYPES inside the isympy shell itself.
+
+Example: isympy -t python
+
+\fITYPE\fR must be one of 'gmpy',
+\&'gmpy1' or 'python'.
+.TP
+\*(T<\fB\-o \fR\*(T>\fIORDER\fR, \*(T<\fB\-\-order=\fR\*(T>\fIORDER\fR
+Setup the ordering of terms for printing. The default is lex, which
+orders terms lexicographically (e.g., x**2 + x + 1). You can choose
+other orderings, such as rev-lex, which will use reverse
+lexicographic ordering (e.g., 1 + x + x**2).
+
+Note that for very large expressions, ORDER='none' may speed up
+printing considerably, with the tradeoff that the order of the terms
+in the printed expression will have no canonical order
+
+Example: isympy -o rev-lax
+
+\fIORDER\fR must be one of 'lex', 'rev-lex', 'grlex',
+\&'rev-grlex', 'grevlex', 'rev-grevlex', 'old', or 'none'.
+.TP
+\*(T<\fB\-q\fR\*(T>, \*(T<\fB\-\-quiet\fR\*(T>
+Print only Python's and SymPy's versions to stdout at startup, and nothing else.
+.TP
+\*(T<\fB\-d\fR\*(T>, \*(T<\fB\-\-doctest\fR\*(T>
+Use the same format that should be used for doctests. This is
+equivalent to '\fIisympy -c python -p no\fR'.
+.TP
+\*(T<\fB\-C\fR\*(T>, \*(T<\fB\-\-no\-cache\fR\*(T>
+Disable the caching mechanism. Disabling the cache may slow certain
+operations down considerably. This is useful for testing the cache,
+or for benchmarking, as the cache can result in deceptive benchmark timings.
+
+This is the same as setting the environment variable SYMPY_USE_CACHE
+to 'no'.
+.TP
+\*(T<\fB\-a\fR\*(T>, \*(T<\fB\-\-auto\fR\*(T>
+Automatically create missing symbols. Normally, typing a name of a
+Symbol that has not been instantiated first would raise NameError,
+but with this option enabled, any undefined name will be
+automatically created as a Symbol. This only works in IPython 0.11.
+
+Note that this is intended only for interactive, calculator style
+usage. In a script that uses SymPy, Symbols should be instantiated
+at the top, so that it's clear what they are.
+
+This will not override any names that are already defined, which
+includes the single character letters represented by the mnemonic
+QCOSINE (see the "Gotchas and Pitfalls" document in the
+documentation). You can delete existing names by executing "del
+name" in the shell itself. You can see if a name is defined by typing
+"'name' in globals()".
+
+The Symbols that are created using this have default assumptions.
+If you want to place assumptions on symbols, you should create them
+using symbols() or var().
+
+Finally, this only works in the top level namespace. So, for
+example, if you define a function in isympy with an undefined
+Symbol, it will not work.
+.TP
+\*(T<\fB\-D\fR\*(T>, \*(T<\fB\-\-debug\fR\*(T>
+Enable debugging output. This is the same as setting the
+environment variable SYMPY_DEBUG to 'True'. The debug status is set
+in the variable SYMPY_DEBUG within isympy.
+.TP
+-- \fIPYTHONOPTIONS\fR
+These options will be passed on to \fIipython (1)\fR shell.
+Only supported when ipython is being used (standard python shell not supported).
+
+Two dashes (--) are required to separate \fIPYTHONOPTIONS\fR
+from the other isympy options.
+
+For example, to run iSymPy without startup banner and colors:
+
+isympy -q -c ipython -- --colors=NoColor
+.TP
+\*(T<\fB\-h\fR\*(T>, \*(T<\fB\-\-help\fR\*(T>
+Print help output and exit.
+.TP
+\*(T<\fB\-v\fR\*(T>, \*(T<\fB\-\-version\fR\*(T>
+Print isympy version information and exit.
+.SH FILES
+.TP
+\*(T<\fI${HOME}/.sympy\-history\fR\*(T>
+Saves the history of commands when using the python
+shell as backend.
+.SH BUGS
+The upstreams BTS can be found at \(lahttps://github.com/sympy/sympy/issues\(ra
+Please report all bugs that you find in there, this will help improve
+the overall quality of SymPy.
+.SH "SEE ALSO"
+\fBipython\fR(1), \fBpython\fR(1)

share/man/man1/ttx.1

@@ -0,0 +1,225 @@
+.Dd May 18, 2004
+.\" ttx is not specific to any OS, but contrary to what groff_mdoc(7)
+.\" seems to imply, entirely omitting the .Os macro causes 'BSD' to
+.\" be used, so I give a zero-width space as its argument.
+.Os \&
+.\" The "FontTools Manual" argument apparently has no effect in
+.\" groff 1.18.1. I think it is a bug in the -mdoc groff package.
+.Dt TTX 1 "FontTools Manual"
+.Sh NAME
+.Nm ttx
+.Nd tool for manipulating TrueType and OpenType fonts
+.Sh SYNOPSIS
+.Nm
+.Bk
+.Op Ar option ...
+.Ek
+.Bk
+.Ar file ...
+.Ek
+.Sh DESCRIPTION
+.Nm
+is a tool for manipulating TrueType and OpenType fonts.  It can convert
+TrueType and OpenType fonts to and from an
+.Tn XML Ns -based format called
+.Tn TTX .
+.Tn TTX
+files have a
+.Ql .ttx
+extension.
+.Pp
+For each
+.Ar file
+argument it is given,
+.Nm
+detects whether it is a
+.Ql .ttf ,
+.Ql .otf
+or
+.Ql .ttx
+file and acts accordingly: if it is a
+.Ql .ttf
+or
+.Ql .otf
+file, it generates a
+.Ql .ttx
+file; if it is a
+.Ql .ttx
+file, it generates a
+.Ql .ttf
+or
+.Ql .otf
+file.
+.Pp
+By default, every output file is created in the same directory as the
+corresponding input file and with the same name except for the
+extension, which is substituted appropriately.
+.Nm
+never overwrites existing files; if necessary, it appends a suffix to
+the output file name before the extension, as in
+.Pa Arial#1.ttf .
+.Ss "General options"
+.Bl -tag -width ".Fl t Ar table"
+.It Fl h
+Display usage information.
+.It Fl d Ar dir
+Write the output files to directory
+.Ar dir
+instead of writing every output file to the same directory as the
+corresponding input file.
+.It Fl o Ar file
+Write the output to
+.Ar file
+instead of writing it to the same directory as the
+corresponding input file.
+.It Fl v
+Be verbose.  Write more messages to the standard output describing what
+is being done.
+.It Fl a
+Allow virtual glyphs ID's on compile or decompile.
+.El
+.Ss "Dump options"
+The following options control the process of dumping font files
+(TrueType or OpenType) to
+.Tn TTX
+files.
+.Bl -tag -width ".Fl t Ar table"
+.It Fl l
+List table information.  Instead of dumping the font to a
+.Tn TTX
+file, display minimal information about each table.
+.It Fl t Ar table
+Dump table
+.Ar table .
+This option may be given multiple times to dump several tables at
+once.  When not specified, all tables are dumped.
+.It Fl x Ar table
+Exclude table
+.Ar table
+from the list of tables to dump.  This option may be given multiple
+times to exclude several tables from the dump.  The
+.Fl t
+and
+.Fl x
+options are mutually exclusive.
+.It Fl s
+Split tables.  Dump each table to a separate
+.Tn TTX
+file and write (under the name that would have been used for the output
+file if the
+.Fl s
+option had not been given) one small
+.Tn TTX
+file containing references to the individual table dump files.  This
+file can be used as input to
+.Nm
+as long as the referenced files can be found in the same directory.
+.It Fl i
+.\" XXX: I suppose OpenType programs (exist and) are also affected.
+Don't disassemble TrueType instructions.  When this option is specified,
+all TrueType programs (glyph programs, the font program and the
+pre-program) are written to the
+.Tn TTX
+file as hexadecimal data instead of
+assembly.  This saves some time and results in smaller
+.Tn TTX
+files.
+.It Fl y Ar n
+When decompiling a TrueType Collection (TTC) file,
+decompile font number
+.Ar n ,
+starting from 0.
+.El
+.Ss "Compilation options"
+The following options control the process of compiling
+.Tn TTX
+files into font files (TrueType or OpenType):
+.Bl -tag -width ".Fl t Ar table"
+.It Fl m Ar fontfile
+Merge the input
+.Tn TTX
+file
+.Ar file
+with
+.Ar fontfile .
+No more than one
+.Ar file
+argument can be specified when this option is used.
+.It Fl b
+Don't recalculate glyph bounding boxes.  Use the values in the
+.Tn TTX
+file as is.
+.El
+.Sh "THE TTX FILE FORMAT"
+You can find some information about the
+.Tn TTX
+file format in
+.Pa documentation.html .
+In particular, you will find in that file the list of tables understood by
+.Nm
+and the relations between TrueType GlyphIDs and the glyph names used in
+.Tn TTX
+files.
+.Sh EXAMPLES
+In the following examples, all files are read from and written to the
+current directory.  Additionally, the name given for the output file
+assumes in every case that it did not exist before
+.Nm
+was invoked.
+.Pp
+Dump the TrueType font contained in
+.Pa FreeSans.ttf
+to
+.Pa FreeSans.ttx :
+.Pp
+.Dl ttx FreeSans.ttf
+.Pp
+Compile
+.Pa MyFont.ttx
+into a TrueType or OpenType font file:
+.Pp
+.Dl ttx MyFont.ttx
+.Pp
+List the tables in
+.Pa FreeSans.ttf
+along with some information:
+.Pp
+.Dl ttx -l FreeSans.ttf
+.Pp
+Dump the
+.Sq cmap
+table from
+.Pa FreeSans.ttf
+to
+.Pa FreeSans.ttx :
+.Pp
+.Dl ttx -t cmap FreeSans.ttf
+.Sh NOTES
+On MS\-Windows and MacOS,
+.Nm
+is available as a graphical application to which files can be dropped.
+.Sh SEE ALSO
+.Pa documentation.html
+.Pp
+.Xr fontforge 1 ,
+.Xr ftinfo 1 ,
+.Xr gfontview 1 ,
+.Xr xmbdfed 1 ,
+.Xr Font::TTF 3pm
+.Sh AUTHORS
+.Nm
+was written by
+.An -nosplit
+.An "Just van Rossum" Aq just@letterror.com .
+.Pp
+This manual page was written by
+.An "Florent Rougon" Aq f.rougon@free.fr
+for the Debian GNU/Linux system based on the existing FontTools
+documentation.  It may be freely used, modified and distributed without
+restrictions.
+.\" For Emacs:
+.\" Local Variables:
+.\" fill-column: 72
+.\" sentence-end: "[.?!][]\"')}]*\\($\\| $\\|   \\|  \\)[   \n]*"
+.\" sentence-end-double-space: t
+.\" End: