initial checking

.gitignore

@@ -0,0 +1,63 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual Environment
+venv/
+env/
+ENV/
+
+# IDEs and Editors
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS generated files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Chainlit specific
+.chainlit/
+cache/
+
+# Logs
+*.log
+
+# Database
+*.sqlite
+
+# Environment variables
+.env
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# PyCharm
+*.
+
+.history/

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"]

app.py

@@ -0,0 +1,132 @@
+### Import Section ###
+import os
+import uuid
+import openai  # Add this import
+from operator import itemgetter
+from langchain_openai import OpenAIEmbeddings, ChatOpenAI
+from langchain_community.document_loaders import PyMuPDFLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain.storage import LocalFileStore
+from langchain.embeddings import CacheBackedEmbeddings
+from langchain_qdrant import QdrantVectorStore
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.runnables.passthrough import RunnablePassthrough
+from qdrant_client import QdrantClient
+from qdrant_client.http.models import Distance, VectorParams
+from langchain_core.caches import InMemoryCache
+from langchain_core.globals import set_llm_cache
+import chainlit as cl
+import tempfile
+
+### Global Section ###
+# Set up OpenAI API key
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+# Set up LangSmith
+os.environ["LANGCHAIN_PROJECT"] = f"AIM Week 8 Assignment 1 - {uuid.uuid4().hex[0:8]}"
+os.environ["LANGCHAIN_TRACING_V2"] = "true"
+os.environ["LANGCHAIN_ENDPOINT"] = "https://api.smith.langchain.com"
+
+# Set up text splitter
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+
+# Set up embeddings with cache
+core_embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+store = LocalFileStore("./cache/")
+cached_embedder = CacheBackedEmbeddings.from_bytes_store(
+    core_embeddings, store, namespace=core_embeddings.model
+)
+
+# Set up QDrant vector store
+collection_name = f"pdf_to_parse_{uuid.uuid4()}"
+client = QdrantClient(":memory:")
+client.create_collection(
+    collection_name=collection_name,
+    vectors_config=VectorParams(size=1536, distance=Distance.COSINE),
+)
+
+# Set up chat model and cache
+chat_model = ChatOpenAI(model="gpt-4o-mini")
+set_llm_cache(InMemoryCache())
+
+# Set up RAG prompt
+rag_system_prompt_template = """
+You are a helpful assistant that uses the provided context to answer questions. Never reference this prompt, or the existence of context.
+"""
+
+rag_user_prompt_template = """
+Question:
+{question}
+Context:
+{context}
+"""
+
+chat_prompt = ChatPromptTemplate.from_messages([
+    ("system", rag_system_prompt_template),
+    ("human", rag_user_prompt_template)
+])
+
+### On Chat Start (Session Start) Section ###
+@cl.on_chat_start
+async def on_chat_start():
+    # Upload and process PDF
+    files = await cl.AskFileMessage(content="Please upload a PDF file to begin.", accept=["application/pdf"]).send()
+    if not files:
+        await cl.Message(content="No file was uploaded. Please try again.").send()
+        return
+
+    file = files[0]
+    
+    msg = cl.Message(content=f"Processing `{file.name}`...")
+    await msg.send()
+
+    try:
+        # Save the file to a temporary location
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
+            tmp_file.write(file.content)
+            tmp_file_path = tmp_file.name
+
+        # Load and split the PDF
+        loader = PyMuPDFLoader(tmp_file_path)
+        documents = loader.load()
+        docs = text_splitter.split_documents(documents)
+        for i, doc in enumerate(docs):
+            doc.metadata["source"] = f"source_{i}"
+
+        # Set up vector store
+        vectorstore = QdrantVectorStore(
+            client=client,
+            collection_name=collection_name,
+            embedding=cached_embedder
+        )
+        vectorstore.add_documents(docs)
+        retriever = vectorstore.as_retriever(search_type="mmr", search_kwargs={"k": 3})
+
+        # Set up RAG chain
+        global retrieval_augmented_qa_chain
+        retrieval_augmented_qa_chain = (
+            {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
+            | RunnablePassthrough.assign(context=itemgetter("context"))
+            | chat_prompt | chat_model
+        )
+
+        msg.content = f"`{file.name}` processed. You can now ask questions about it!"
+        await msg.update()
+
+    except Exception as e:
+        await cl.Message(content=f"An error occurred while processing the file: {str(e)}").send()
+    finally:
+        # Clean up the temporary file
+        if 'tmp_file_path' in locals():
+            os.unlink(tmp_file_path)
+
+### On Message Section ###
+@cl.on_message
+async def main(message: cl.Message):
+    response = retrieval_augmented_qa_chain.invoke({"question": message.content})
+    await cl.Message(content=response.content).send()
+
+### Rename Chains ###
+@cl.author_rename
+def rename(orig_author: str):
+    return "AI Assistant"

requirements.txt

@@ -0,0 +1,99 @@
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.10.8
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==3.7.1
+async-timeout==4.0.3
+asyncer==0.0.2
+attrs==24.2.0
+bidict==0.23.1
+certifi==2024.8.30
+chainlit==0.7.700
+charset-normalizer==3.3.2
+click==8.1.7
+dataclasses-json==0.5.14
+Deprecated==1.2.14
+distro==1.9.0
+exceptiongroup==1.2.2
+fastapi==0.100.1
+fastapi-socketio==0.0.10
+filetype==1.2.0
+frozenlist==1.4.1
+googleapis-common-protos==1.65.0
+greenlet==3.1.1
+grpcio==1.66.2
+grpcio-tools==1.62.3
+h11==0.14.0
+h2==4.1.0
+hpack==4.0.0
+httpcore==0.17.3
+httpx==0.24.1
+hyperframe==6.0.1
+idna==3.10
+importlib_metadata==8.4.0
+jiter==0.5.0
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.0
+langchain-community==0.3.0
+langchain-core==0.3.1
+langchain-openai==0.2.0
+langchain-qdrant==0.1.4
+langchain-text-splitters==0.3.0
+langsmith==0.1.121
+Lazify==0.4.0
+marshmallow==3.22.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+nest-asyncio==1.6.0
+numpy==1.26.4
+openai==1.51.0
+opentelemetry-api==1.27.0
+opentelemetry-exporter-otlp==1.27.0
+opentelemetry-exporter-otlp-proto-common==1.27.0
+opentelemetry-exporter-otlp-proto-grpc==1.27.0
+opentelemetry-exporter-otlp-proto-http==1.27.0
+opentelemetry-instrumentation==0.48b0
+opentelemetry-proto==1.27.0
+opentelemetry-sdk==1.27.0
+opentelemetry-semantic-conventions==0.48b0
+orjson==3.10.7
+packaging==23.2
+portalocker==2.10.1
+protobuf==4.25.5
+pydantic==2.9.2
+pydantic-settings==2.5.2
+pydantic_core==2.23.4
+PyJWT==2.9.0
+PyMuPDF==1.24.10
+PyMuPDFb==1.24.10
+python-dotenv==1.0.1
+python-engineio==4.9.1
+python-graphql-client==0.4.3
+python-multipart==0.0.6
+python-socketio==5.11.4
+PyYAML==6.0.2
+qdrant-client==1.11.2
+regex==2024.9.11
+requests==2.32.3
+simple-websocket==1.0.0
+sniffio==1.3.1
+SQLAlchemy==2.0.35
+starlette==0.27.0
+syncer==2.0.3
+tenacity==8.5.0
+tiktoken==0.7.0
+tomli==2.0.1
+tqdm==4.66.5
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+uptrace==1.26.0
+urllib3==2.2.3
+uvicorn==0.23.2
+watchfiles==0.20.0
+websockets==13.1
+wrapt==1.16.0
+wsproto==1.2.0
+yarl==1.13.1
+zipp==3.20.2