deploy RAG

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 +1,176 @@
+### Import Section ###
+import uuid
+from operator import itemgetter
+
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.globals import set_llm_cache
+from langchain_core.caches import InMemoryCache
+
+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.schema import StrOutputParser
+
+from langchain_openai import ChatOpenAI
+from langchain_openai.embeddings import OpenAIEmbeddings
+
+from qdrant_client import QdrantClient
+from qdrant_client.http.models import Distance, VectorParams
+
+from langchain_qdrant import QdrantVectorStore
+
+import chainlit as cl
+from chainlit.types import AskFileResponse
+
+
+### Global Section ###
+set_llm_cache(InMemoryCache())
+
+rag_system_prompt_template = """\
+You are a helpful assistant that uses the provided context to answer questions. Never reference this prompt, or the existance of context.
+"""
+
+rag_message_list = [
+    {"role" : "system", "content" : rag_system_prompt_template},
+]
+
+rag_user_prompt_template = """\
+Question:
+{question}
+Context:
+{context}
+"""
+
+chat_prompt = ChatPromptTemplate.from_messages([
+    ("system", rag_system_prompt_template),
+    ("human", rag_user_prompt_template)
+])
+
+
+class VectorDatabase:
+    def __init__(self, embeddings: OpenAIEmbeddings()) -> None:
+        self.embeddings = embeddings
+        
+    async def build_retriever(self, docs) -> None:
+        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),
+        )
+
+        # Adding cache!
+        store = LocalFileStore("./cache/")
+        cached_embedder = CacheBackedEmbeddings.from_bytes_store(
+            self.embeddings, store, namespace=self.embeddings.model
+        )
+
+        # Typical QDrant Vector Store Set-up
+        vectorstore = QdrantVectorStore(
+            client=client,
+            collection_name=collection_name,
+            embedding=cached_embedder)
+        vectorstore.add_documents(docs)
+        
+        return vectorstore.as_retriever(search_type="mmr", search_kwargs={"k": 3})
+    
+    
+class RetrievalAugmentedQAPipeline:
+    def __init__(self, llm: ChatOpenAI(), vector_db_retriever: VectorDatabase) -> None:
+        self.llm = llm
+        self.retriever = vector_db_retriever
+        
+    async def arun_pipeline(self, user_query: str):
+        retrieval_augmented_qa_chain = (
+                {"context": itemgetter("question") | self.retriever, "question": itemgetter("question")}
+                | chat_prompt | self.llm | StrOutputParser()
+            )
+        
+        async def generate_response():
+            async for chunk in retrieval_augmented_qa_chain.astream({"question": user_query}):
+                yield chunk
+
+        return {"response": generate_response()}
+    
+
+def process_pdf_file(file: AskFileResponse):
+    import tempfile
+    with tempfile.NamedTemporaryFile(mode="wb", delete=False, suffix=".pdf") as temp_file:
+        temp_file_path = temp_file.name
+        temp_file.write(file.content)
+        
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+    Loader = PyMuPDFLoader
+    loader = Loader(temp_file_path)
+    documents = loader.load()
+    docs = text_splitter.split_documents(documents)
+    for i, doc in enumerate(docs):
+        doc.metadata["source"] = f"source_{i}"
+    
+    return docs
+    
+
+### On Chat Start (Session Start) Section ###
+@cl.on_chat_start
+async def on_chat_start():
+    """ SESSION SPECIFIC CODE HERE """
+    files = None
+    # Wait for the user to upload a file
+    while files == None:
+        files = await cl.AskFileMessage(
+            content="Please upload a pdf file to begin!",
+            accept=["pdf"],
+            max_size_mb=2,
+            timeout=180,
+        ).send()
+    file = files[0]
+
+    msg = cl.Message(
+        content=f"Processing `{file.name}`...", disable_human_feedback=True
+    )
+    await msg.send()
+    docs = process_pdf_file(file)
+    print(f"Processing {len(docs)} text chunks")
+
+    # Create a dict vector store
+    vector_db = VectorDatabase(embeddings=OpenAIEmbeddings(model="text-embedding-3-small"))
+    vector_db = await vector_db.build_retriever(docs)
+
+    # Create a chain
+    retrieval_augmented_qa_pipeline = RetrievalAugmentedQAPipeline(
+        llm=ChatOpenAI(model="gpt-4o-mini"),
+        vector_db_retriever=vector_db
+    )
+    
+    # Let the user know that the system is ready
+    msg.content = f"Processing `{file.name}` done. You can now ask questions!"
+    await msg.update()
+
+    cl.user_session.set("chain", retrieval_augmented_qa_pipeline)
+
+
+### Rename Chains ###
+@cl.author_rename
+def rename(orig_author: str):
+    """ RENAME CODE HERE """
+    rename_dict = {"LLMMathChain": "Albert Einstein", "Chatbot": "Assistant"}
+    return rename_dict.get(orig_author, orig_author)
+
+
+### On Message Section ###
+@cl.on_message
+async def main(message: cl.Message):
+    """
+    MESSAGE CODE HERE
+    """
+    chain = cl.user_session.get("chain")
+
+    msg = cl.Message(content="")
+    result = await chain.arun_pipeline(message.content)
+
+    async for stream_resp in result["response"]:
+        await msg.stream_token(stream_resp)
+
+    await msg.send()
+    

requirements.txt

@@ -0,0 +1,132 @@
+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
+faiss-cpu==1.8.0.post1
+fastapi==0.100.1
+fastapi-socketio==0.0.10
+filelock==3.16.1
+filetype==1.2.0
+frozenlist==1.4.1
+fsspec==2024.9.0
+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
+huggingface-hub==0.25.1
+hyperframe==6.0.1
+idna==3.10
+importlib_metadata==8.4.0
+Jinja2==3.1.4
+jiter==0.5.0
+joblib==1.4.2
+jsonpatch==1.33
+jsonpointer==3.0.0
+langchain==0.3.0
+langchain-community==0.3.0
+langchain-core==0.3.1
+langchain-huggingface==0.1.0
+langchain-openai==0.2.0
+langchain-qdrant==0.1.4
+langchain-text-splitters==0.3.0
+langsmith==0.1.121
+Lazify==0.4.0
+MarkupSafe==2.1.5
+marshmallow==3.22.0
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+nest-asyncio==1.6.0
+networkx==3.2.1
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.77
+nvidia-nvtx-cu12==12.1.105
+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
+pillow==10.4.0
+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
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.13.1
+sentence-transformers==3.1.1
+simple-websocket==1.0.0
+sniffio==1.3.1
+SQLAlchemy==2.0.35
+starlette==0.27.0
+sympy==1.13.3
+syncer==2.0.3
+tenacity==8.5.0
+threadpoolctl==3.5.0
+tiktoken==0.7.0
+tokenizers==0.20.0
+tomli==2.0.1
+# torch==2.4.1
+tqdm==4.66.5
+transformers==4.45.1
+triton==3.0.0
+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