first commit

.chainlit/config.toml

@@ -0,0 +1,84 @@
+[project]
+# Whether to enable telemetry (default: true). No personal data is collected.
+enable_telemetry = true
+
+# List of environment variables to be provided by each user to use the app.
+user_env = []
+
+# Duration (in seconds) during which the session is saved when the connection is lost
+session_timeout = 3600
+
+# Enable third parties caching (e.g LangChain cache)
+cache = false
+
+# Follow symlink for asset mount (see https://github.com/Chainlit/chainlit/issues/317)
+# follow_symlink = false
+
+[features]
+# Show the prompt playground
+prompt_playground = false
+
+# Process and display HTML in messages. This can be a security risk (see https://stackoverflow.com/questions/19603097/why-is-it-dangerous-to-render-user-generated-html-or-javascript)
+unsafe_allow_html = false
+
+# Process and display mathematical expressions. This can clash with "$" characters in messages.
+latex = false
+
+# Authorize users to upload files with messages
+multi_modal = false
+
+# Allows user to use speech to text
+[features.speech_to_text]
+    enabled = false
+    # See all languages here https://github.com/JamesBrill/react-speech-recognition/blob/HEAD/docs/API.md#language-string
+    # language = "en-US"
+
+[UI]
+# Name of the app and chatbot.
+name = "Sage"
+
+# Show the readme while the conversation is empty.
+show_readme_as_default = false
+
+# Description of the app and chatbot. This is used for HTML tags.
+# description = ""
+
+# Large size content are by default collapsed for a cleaner ui
+default_collapse_content = true
+
+# The default value for the expand messages settings.
+default_expand_messages = false
+
+# Hide the chain of thought details from the user in the UI.
+hide_cot = false
+
+# Link to your github repo. This will add a github button in the UI's header.
+# github = ""
+
+# Specify a CSS file that can be used to customize the user interface.
+# The CSS file can be served from the public directory or via an external link.
+# custom_css = "/public/test.css"
+
+# Override default MUI light theme. (Check theme.ts)
+[UI.theme.light]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.light.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+# Override default MUI dark theme. (Check theme.ts)
+[UI.theme.dark]
+    #background = "#FAFAFA"
+    #paper = "#FFFFFF"
+
+    [UI.theme.dark.primary]
+        #main = "#F80061"
+        #dark = "#980039"
+        #light = "#FFE7EB"
+
+
+[meta]
+generated_by = "0.7.700"

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
+COPY --chown=user . $HOME/app
+COPY ./requirements.txt ~/app/requirements.txt
+RUN pip install -r requirements.txt
+COPY . .
+CMD ["chainlit", "run", "app.py", "--port", "7860"]

README.md

@@ -0,0 +1,3 @@
+# DocuSage
+
+DocuSage is a powerful document question-answering application that allows users to upload documents and ask natural language questions about their content. With cutting-edge AI technology, DocuSage provides accurate, concise answers in seconds, saving time and boosting productivity. Unlock valuable insights and let DocuSage be your sage guide through the world of document knowledge.

app.py

@@ -0,0 +1,29 @@
+import os
+import chainlit as cl 
+from chain import rag_chain
+from langchain.schema.runnable import RunnableConfig
+
+
+welcome_message = "Welcome! Ask anything about your stored documents and get AI-powered insights in seconds."
+
+@cl.on_chat_start  
+async def start_chat():
+    await cl.Message(content=welcome_message).send()
+
+    cl.user_session.set("runnable", rag_chain)
+
+
+@cl.on_message 
+async def main(message: cl.Message):
+    runnable = cl.user_session.get("runnable")
+    msg = cl.Message(content="")
+
+    async for chunk in runnable.astream(
+        message.content,
+        config=RunnableConfig(callbacks=[
+            cl.LangchainCallbackHandler()
+        ]),
+    ):
+        await msg.stream_token(chunk)
+
+    await msg.send()

chain.py

@@ -0,0 +1,74 @@
+# Langchain imports
+from langchain_community.document_loaders import PyMuPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Qdrant
+from langchain.prompts import ChatPromptTemplate
+from langchain_openai import ChatOpenAI
+from langchain_openai import OpenAIEmbeddings
+from langchain_core.output_parsers import StrOutputParser
+from langchain.schema.runnable import RunnablePassthrough
+from dotenv import load_dotenv
+
+
+load_dotenv()
+
+######################## Build RAG Chain #############################
+######################################################################
+
+#### Load  Documents
+# loader = PyMuPDFLoader(
+#     "./data/c7318154-f6ae-4866-89fa-f0c589f2ee3d.pdf",
+# )
+loader = PyMuPDFLoader(
+    "https://d18rn0p25nwr6d.cloudfront.net/CIK-0001326801/c7318154-f6ae-4866-89fa-f0c589f2ee3d.pdf"
+)
+
+documents = loader.load()
+
+#### Split Documents
+text_splitter = RecursiveCharacterTextSplitter(
+    chunk_size = 800,
+    chunk_overlap = 100
+)
+
+documents = text_splitter.split_documents(documents)
+
+embeddings = OpenAIEmbeddings(
+    model="text-embedding-3-small"
+)
+
+###  Create Vector Store
+vector_store = Qdrant.from_documents(
+    documents,
+    embeddings,
+    location=":memory:",
+    collection_name="Meta 10k Filings",
+)
+
+### Create Prmopt Template
+template = """Answer the question based only on the following context. If you cannot answer the question with the context, please respond with 'I don't know':
+
+Context:
+{context}
+
+Question:
+{question}
+"""
+prompt = ChatPromptTemplate.from_template(template)
+
+def format_docs(docs):
+    return "\n\n".join([d.page_content for d in docs])
+
+### Setup RAG Chain
+
+retriever = vector_store.as_retriever(search_type="similarity_score_threshold", 
+                                      search_kwargs={"score_threshold": 0.6, "k":8})
+primary_qa_llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)
+
+rag_chain = (
+    {"context": retriever | format_docs, "question": RunnablePassthrough()}
+    | prompt 
+    | primary_qa_llm
+    | StrOutputParser()
+
+)

chainlit.md

@@ -0,0 +1,3 @@
+# DocuSage
+
+DocuSage is a powerful document question-answering application that allows users to upload documents and ask natural language questions about their content. With cutting-edge AI technology, DocuSage provides accurate, concise answers in seconds, saving time and boosting productivity. Unlock valuable insights and let DocuSage be your sage guide through the world of document knowledge.

requirements.txt

@@ -0,0 +1,13 @@
+chainlit
+tiktoken
+python-dotenv
+langchain 
+langchain-openai 
+langchain_core 
+langchain-community 
+langchainhub
+openai
+qdrant-client 
+pymupdf 
+pandas
+unstructured[pdf]

tests/test_chain.py

@@ -0,0 +1,10 @@
+import unittest
+from chain import rag_chain
+
+class TestRAGChain(unittest.TestCase):
+
+    def test_rag_chain(self):
+        ans = rag_chain.invoke("Who are Meta's 'Directors' (i.e., members of the Board of Directors)?")
+
+if __name__ == '__main__':
+    unittest.main()