Spaces:
Running
Running
jeonghin
commited on
Commit
•
f880c97
1
Parent(s):
429e86f
Initial commit
Browse files- .gitignore +171 -0
- app.py +202 -0
- requirements.txt +81 -0
.gitignore
ADDED
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Byte-compiled / optimized / DLL files
|
2 |
+
__pycache__/
|
3 |
+
*.py[cod]
|
4 |
+
*$py.class
|
5 |
+
|
6 |
+
# C extensions
|
7 |
+
*.so
|
8 |
+
|
9 |
+
# Distribution / packaging
|
10 |
+
.Python
|
11 |
+
build/
|
12 |
+
develop-eggs/
|
13 |
+
dist/
|
14 |
+
downloads/
|
15 |
+
eggs/
|
16 |
+
.eggs/
|
17 |
+
lib/
|
18 |
+
lib64/
|
19 |
+
parts/
|
20 |
+
sdist/
|
21 |
+
var/
|
22 |
+
wheels/
|
23 |
+
share/python-wheels/
|
24 |
+
*.egg-info/
|
25 |
+
.installed.cfg
|
26 |
+
*.egg
|
27 |
+
MANIFEST
|
28 |
+
|
29 |
+
# PyInstaller
|
30 |
+
# Usually these files are written by a python script from a template
|
31 |
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
32 |
+
*.manifest
|
33 |
+
*.spec
|
34 |
+
|
35 |
+
# Installer logs
|
36 |
+
pip-log.txt
|
37 |
+
pip-delete-this-directory.txt
|
38 |
+
|
39 |
+
# Unit test / coverage reports
|
40 |
+
htmlcov/
|
41 |
+
.tox/
|
42 |
+
.nox/
|
43 |
+
.coverage
|
44 |
+
.coverage.*
|
45 |
+
.cache
|
46 |
+
nosetests.xml
|
47 |
+
coverage.xml
|
48 |
+
*.cover
|
49 |
+
*.py,cover
|
50 |
+
.hypothesis/
|
51 |
+
.pytest_cache/
|
52 |
+
cover/
|
53 |
+
|
54 |
+
# Translations
|
55 |
+
*.mo
|
56 |
+
*.pot
|
57 |
+
|
58 |
+
# Django stuff:
|
59 |
+
*.log
|
60 |
+
local_settings.py
|
61 |
+
db.sqlite3
|
62 |
+
db.sqlite3-journal
|
63 |
+
|
64 |
+
# Flask stuff:
|
65 |
+
instance/
|
66 |
+
.webassets-cache
|
67 |
+
|
68 |
+
# Scrapy stuff:
|
69 |
+
.scrapy
|
70 |
+
|
71 |
+
# Sphinx documentation
|
72 |
+
docs/_build/
|
73 |
+
|
74 |
+
# PyBuilder
|
75 |
+
.pybuilder/
|
76 |
+
target/
|
77 |
+
|
78 |
+
# Jupyter Notebook
|
79 |
+
.ipynb_checkpoints
|
80 |
+
|
81 |
+
# IPython
|
82 |
+
profile_default/
|
83 |
+
ipython_config.py
|
84 |
+
|
85 |
+
# pyenv
|
86 |
+
# For a library or package, you might want to ignore these files since the code is
|
87 |
+
# intended to run in multiple environments; otherwise, check them in:
|
88 |
+
# .python-version
|
89 |
+
|
90 |
+
# pipenv
|
91 |
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
92 |
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
93 |
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
94 |
+
# install all needed dependencies.
|
95 |
+
#Pipfile.lock
|
96 |
+
|
97 |
+
# poetry
|
98 |
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
99 |
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
100 |
+
# commonly ignored for libraries.
|
101 |
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
102 |
+
#poetry.lock
|
103 |
+
|
104 |
+
# pdm
|
105 |
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
106 |
+
#pdm.lock
|
107 |
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
108 |
+
# in version control.
|
109 |
+
# https://pdm.fming.dev/#use-with-ide
|
110 |
+
.pdm.toml
|
111 |
+
|
112 |
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
113 |
+
__pypackages__/
|
114 |
+
|
115 |
+
# Celery stuff
|
116 |
+
celerybeat-schedule
|
117 |
+
celerybeat.pid
|
118 |
+
|
119 |
+
# SageMath parsed files
|
120 |
+
*.sage.py
|
121 |
+
|
122 |
+
# Environments
|
123 |
+
.env
|
124 |
+
.venv
|
125 |
+
env/
|
126 |
+
venv/
|
127 |
+
ENV/
|
128 |
+
env.bak/
|
129 |
+
venv.bak/
|
130 |
+
birdseye_venv/
|
131 |
+
birdseye/migrations/
|
132 |
+
|
133 |
+
# Spyder project settings
|
134 |
+
.spyderproject
|
135 |
+
.spyproject
|
136 |
+
|
137 |
+
# Rope project settings
|
138 |
+
.ropeproject
|
139 |
+
|
140 |
+
# mkdocs documentation
|
141 |
+
/site
|
142 |
+
|
143 |
+
# mypy
|
144 |
+
.mypy_cache/
|
145 |
+
.dmypy.json
|
146 |
+
dmypy.json
|
147 |
+
|
148 |
+
# Pyre type checker
|
149 |
+
.pyre/
|
150 |
+
|
151 |
+
# pytype static type analyzer
|
152 |
+
.pytype/
|
153 |
+
|
154 |
+
# Cython debug symbols
|
155 |
+
cython_debug/
|
156 |
+
|
157 |
+
# PyCharm
|
158 |
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
159 |
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
160 |
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
161 |
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
162 |
+
#.idea/
|
163 |
+
|
164 |
+
# MacOS
|
165 |
+
.DS_Store
|
166 |
+
|
167 |
+
# Certificate
|
168 |
+
Birdseye.pem
|
169 |
+
Birdseye2.pem
|
170 |
+
|
171 |
+
RECOVERY-CODES-Jeong Hin Chin.txt
|
app.py
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
|
3 |
+
# from htmlTemplates import css, bot_template, user_template
|
4 |
+
|
5 |
+
from dotenv import load_dotenv
|
6 |
+
|
7 |
+
# from PyPDF2 import PdfReader
|
8 |
+
|
9 |
+
import os
|
10 |
+
import mysql.connector
|
11 |
+
|
12 |
+
from langchain.text_splitter import CharacterTextSplitter
|
13 |
+
from langchain_community.embeddings import HuggingFaceInstructEmbeddings
|
14 |
+
from langchain_community.vectorstores import FAISS
|
15 |
+
from langchain_community.llms import HuggingFaceHub
|
16 |
+
from langchain_openai import ChatOpenAI
|
17 |
+
from langchain_openai import OpenAIEmbeddings
|
18 |
+
from langchain.memory import ConversationBufferMemory
|
19 |
+
from langchain.chains import ConversationalRetrievalChain
|
20 |
+
|
21 |
+
|
22 |
+
def get_pdf_text(slug):
|
23 |
+
load_dotenv()
|
24 |
+
|
25 |
+
text = ""
|
26 |
+
try:
|
27 |
+
conn = mysql.connector.connect(
|
28 |
+
user=os.getenv("SQL_USER"),
|
29 |
+
password=os.getenv("SQL_PWD"),
|
30 |
+
host=os.getenv("SQL_HOST"),
|
31 |
+
database="Birdseye_DB",
|
32 |
+
)
|
33 |
+
cursor = conn.cursor()
|
34 |
+
|
35 |
+
# Execute a query
|
36 |
+
cursor.execute("SELECT ocr_text FROM birdseye_temp WHERE slug = %s", (slug,))
|
37 |
+
|
38 |
+
# Fetch the results
|
39 |
+
rows = cursor.fetchall()
|
40 |
+
for row in rows:
|
41 |
+
if row[0]:
|
42 |
+
text += row[0]
|
43 |
+
|
44 |
+
except mysql.connector.Error as err:
|
45 |
+
st.error(f"Error: {err}")
|
46 |
+
finally:
|
47 |
+
if conn.is_connected():
|
48 |
+
cursor.close()
|
49 |
+
conn.close()
|
50 |
+
return text
|
51 |
+
|
52 |
+
|
53 |
+
def get_text_chunks(text):
|
54 |
+
"""
|
55 |
+
Splits the given text into chunks based on specified character settings.
|
56 |
+
Parameters:
|
57 |
+
- text (str): The text to be split into chunks.
|
58 |
+
Returns:
|
59 |
+
- list: A list of text chunks.
|
60 |
+
"""
|
61 |
+
text_splitter = CharacterTextSplitter(
|
62 |
+
separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len
|
63 |
+
)
|
64 |
+
chunks = text_splitter.split_text(text)
|
65 |
+
return chunks
|
66 |
+
|
67 |
+
|
68 |
+
def get_vectorstore(text_chunks):
|
69 |
+
"""
|
70 |
+
Generates a vector store from a list of text chunks using specified embeddings.
|
71 |
+
Parameters:
|
72 |
+
- text_chunks (list of str): Text segments to convert into vector embeddings.
|
73 |
+
Returns:
|
74 |
+
- FAISS: A FAISS vector store containing the embeddings of the text chunks.
|
75 |
+
"""
|
76 |
+
embeddings = OpenAIEmbeddings()
|
77 |
+
vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
|
78 |
+
return vectorstore
|
79 |
+
|
80 |
+
|
81 |
+
def get_conversation_chain(vectorstore):
|
82 |
+
"""
|
83 |
+
Initializes a conversational retrieval chain that uses a large language model
|
84 |
+
for generating responses based on the provided vector store.
|
85 |
+
Parameters:
|
86 |
+
- vectorstore (FAISS): A vector store to be used for retrieving relevant content.
|
87 |
+
Returns:
|
88 |
+
- ConversationalRetrievalChain: An initialized conversational chain object.
|
89 |
+
"""
|
90 |
+
try:
|
91 |
+
llm = ChatOpenAI(model_name="gpt-4-1106-preview")
|
92 |
+
memory = ConversationBufferMemory(
|
93 |
+
memory_key="chat_history", return_messages=True
|
94 |
+
)
|
95 |
+
conversation_chain = ConversationalRetrievalChain.from_llm(
|
96 |
+
llm=llm, retriever=vectorstore.as_retriever(), memory=memory
|
97 |
+
)
|
98 |
+
return conversation_chain
|
99 |
+
except Exception as e:
|
100 |
+
raise # Re-raise exception to handle it or log it properly elsewhere
|
101 |
+
|
102 |
+
|
103 |
+
def handle_userinput(user_question):
|
104 |
+
response = st.session_state.conversation(
|
105 |
+
{
|
106 |
+
"question": f"Based on the memory and the provided document, answer the following user question: {user_question}. If the question is unrelated to memory or the document, just mention that you cannot provide an answer."
|
107 |
+
}
|
108 |
+
)
|
109 |
+
st.session_state.chat_history = response["chat_history"]
|
110 |
+
|
111 |
+
for i, message in reversed(list(enumerate(st.session_state.chat_history))):
|
112 |
+
if i % 2 == 0:
|
113 |
+
st.write(
|
114 |
+
user_template.replace("{{MSG}}", message.content),
|
115 |
+
unsafe_allow_html=True,
|
116 |
+
)
|
117 |
+
else:
|
118 |
+
st.write(
|
119 |
+
bot_template.replace("{{MSG}}", message.content), unsafe_allow_html=True
|
120 |
+
)
|
121 |
+
|
122 |
+
|
123 |
+
def chat(slug):
|
124 |
+
"""
|
125 |
+
Manages the chat interface in the Streamlit application, handling the conversation
|
126 |
+
flow and displaying the chat history.
|
127 |
+
"""
|
128 |
+
|
129 |
+
text_chunks = get_text_chunks(get_pdf_text(slug))
|
130 |
+
vectorstore = get_vectorstore(text_chunks)
|
131 |
+
st.session_state.conversation = get_conversation_chain(vectorstore)
|
132 |
+
|
133 |
+
if len(st.session_state.messages) == 1:
|
134 |
+
message = st.session_state.messages[0]
|
135 |
+
with st.chat_message(message["role"]):
|
136 |
+
st.write(message["content"])
|
137 |
+
|
138 |
+
else:
|
139 |
+
for message in st.session_state.messages:
|
140 |
+
with st.chat_message(message["role"]):
|
141 |
+
st.write(message["content"])
|
142 |
+
|
143 |
+
# User-provided prompt
|
144 |
+
if prompt := st.chat_input():
|
145 |
+
st.session_state.messages.append({"role": "user", "content": prompt})
|
146 |
+
st.session_state.prompts = prompt
|
147 |
+
with st.chat_message("user"):
|
148 |
+
st.write(prompt)
|
149 |
+
|
150 |
+
if st.session_state.messages[-1]["role"] != "system":
|
151 |
+
|
152 |
+
with st.spinner("Generating response..."):
|
153 |
+
response = st.session_state.conversation.invoke(
|
154 |
+
{"question": st.session_state.prompts}
|
155 |
+
)
|
156 |
+
|
157 |
+
with st.chat_message("system"):
|
158 |
+
message_content = response["chat_history"][-1].content
|
159 |
+
st.session_state.messages.append(
|
160 |
+
{"role": "system", "content": message_content}
|
161 |
+
)
|
162 |
+
st.write(message_content)
|
163 |
+
|
164 |
+
|
165 |
+
def init():
|
166 |
+
"""
|
167 |
+
Initializes the session state variables used in the Streamlit application and
|
168 |
+
loads environment variables.
|
169 |
+
"""
|
170 |
+
|
171 |
+
if "pdf" not in st.session_state:
|
172 |
+
st.session_state["pdf"] = False
|
173 |
+
if "conversation" not in st.session_state:
|
174 |
+
st.session_state.conversation = None
|
175 |
+
if "chat_history" not in st.session_state:
|
176 |
+
st.session_state.chat_history = None
|
177 |
+
if "messages" not in st.session_state.keys():
|
178 |
+
st.session_state.messages = [
|
179 |
+
{
|
180 |
+
"role": "system",
|
181 |
+
"content": "What do you want to learn about the document? Ask me a question!",
|
182 |
+
}
|
183 |
+
]
|
184 |
+
|
185 |
+
|
186 |
+
def main():
|
187 |
+
init()
|
188 |
+
query_params = st.query_params
|
189 |
+
slug = query_params.get("slug")
|
190 |
+
|
191 |
+
load_dotenv()
|
192 |
+
st.title("Chat with GPT :books:")
|
193 |
+
|
194 |
+
if slug:
|
195 |
+
chat(slug)
|
196 |
+
|
197 |
+
else:
|
198 |
+
st.error("Please return to Birdseye and select a document.")
|
199 |
+
|
200 |
+
|
201 |
+
if __name__ == "__main__":
|
202 |
+
main()
|
requirements.txt
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
aiohttp==3.9.5
|
2 |
+
aiosignal==1.3.1
|
3 |
+
altair==4.0.0
|
4 |
+
annotated-types==0.6.0
|
5 |
+
anyio==4.3.0
|
6 |
+
attrs==23.2.0
|
7 |
+
blinker==1.8.1
|
8 |
+
cachetools==5.3.3
|
9 |
+
certifi==2024.2.2
|
10 |
+
charset-normalizer==3.3.2
|
11 |
+
click==8.1.7
|
12 |
+
dataclasses-json==0.6.5
|
13 |
+
distro==1.9.0
|
14 |
+
entrypoints==0.4
|
15 |
+
faiss-cpu==1.7.4
|
16 |
+
frozenlist==1.4.1
|
17 |
+
gitdb==4.0.11
|
18 |
+
GitPython==3.1.43
|
19 |
+
h11==0.14.0
|
20 |
+
httpcore==1.0.5
|
21 |
+
httpx==0.27.0
|
22 |
+
idna==3.7
|
23 |
+
Jinja2==3.1.4
|
24 |
+
jsonpatch==1.33
|
25 |
+
jsonpointer==2.4
|
26 |
+
jsonschema==4.22.0
|
27 |
+
jsonschema-specifications==2023.12.1
|
28 |
+
langchain==0.1.16
|
29 |
+
langchain-community==0.0.32
|
30 |
+
langchain-core==0.1.42
|
31 |
+
langchain-openai==0.1.3
|
32 |
+
langchain-text-splitters==0.0.1
|
33 |
+
langsmith==0.1.54
|
34 |
+
markdown-it-py==3.0.0
|
35 |
+
MarkupSafe==2.1.5
|
36 |
+
marshmallow==3.21.2
|
37 |
+
mdurl==0.1.2
|
38 |
+
multidict==6.0.5
|
39 |
+
mypy-extensions==1.0.0
|
40 |
+
mysql==0.0.3
|
41 |
+
mysql-connector-python==8.4.0
|
42 |
+
mysql-connector-python-rf==2.2.2
|
43 |
+
mysqlclient==2.2.0
|
44 |
+
numpy==1.26.4
|
45 |
+
openai==1.25.2
|
46 |
+
orjson==3.10.3
|
47 |
+
packaging==23.2
|
48 |
+
pandas==2.2.2
|
49 |
+
pillow==10.3.0
|
50 |
+
protobuf==4.25.3
|
51 |
+
pyarrow==16.0.0
|
52 |
+
pydantic==2.7.1
|
53 |
+
pydantic_core==2.18.2
|
54 |
+
pydeck==0.9.0
|
55 |
+
Pygments==2.18.0
|
56 |
+
PyPDF2==3.0.1
|
57 |
+
python-dateutil==2.9.0.post0
|
58 |
+
python-dotenv==1.0.0
|
59 |
+
pytz==2024.1
|
60 |
+
PyYAML==6.0.1
|
61 |
+
referencing==0.35.1
|
62 |
+
regex==2024.4.28
|
63 |
+
requests==2.31.0
|
64 |
+
rich==13.7.1
|
65 |
+
rpds-py==0.18.0
|
66 |
+
six==1.16.0
|
67 |
+
smmap==5.0.1
|
68 |
+
sniffio==1.3.1
|
69 |
+
SQLAlchemy==2.0.30
|
70 |
+
streamlit==1.33.0
|
71 |
+
tenacity==8.2.3
|
72 |
+
tiktoken==0.6.0
|
73 |
+
toml==0.10.2
|
74 |
+
toolz==0.12.1
|
75 |
+
tornado==6.4
|
76 |
+
tqdm==4.66.4
|
77 |
+
typing-inspect==0.9.0
|
78 |
+
typing_extensions==4.11.0
|
79 |
+
tzdata==2024.1
|
80 |
+
urllib3==2.2.1
|
81 |
+
yarl==1.9.4
|