First commit

.gitignore

@@ -0,0 +1,2 @@
+venv/
+.vscode/

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 +1,184 @@
+### Import Section ###
+"""
+IMPORTS HERE
+"""
+import os
+import uuid
+from dotenv import load_dotenv
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import PyMuPDFLoader
+from qdrant_client import QdrantClient
+from qdrant_client.http.models import Distance, VectorParams
+from langchain_openai.embeddings import OpenAIEmbeddings
+from langchain.storage import LocalFileStore
+from langchain_qdrant import QdrantVectorStore
+from langchain.embeddings import CacheBackedEmbeddings
+from langchain_core.prompts import ChatPromptTemplate
+from chainlit.types import AskFileResponse
+from langchain_core.globals import set_llm_cache
+from langchain_openai import ChatOpenAI
+from langchain_core.caches import InMemoryCache
+from operator import itemgetter
+from langchain_core.runnables.passthrough import RunnablePassthrough
+import chainlit as cl
+from langchain_core.runnables.config import RunnableConfig
+from langchain_community.llms import HuggingFaceEndpoint
+from langchain_huggingface.embeddings import HuggingFaceEndpointEmbeddings
+from langchain_core.prompts import PromptTemplate
+
+import numpy as np
+from numpy.linalg import norm
+
+load_dotenv()
+
+### Global Section ###
+"""
+GLOBAL CODE HERE
+"""
+
+RAG_PROMPT_TEMPLATE = """\
+<|start_header_id|>system<|end_header_id|>
+You are a helpful assistant. You answer user questions based on provided context. If you can't answer the question with the provided context, say you don't know.<|eot_id|>
+
+<|start_header_id|>user<|end_header_id|>
+User Query:
+{query}
+
+Context:
+{context}<|eot_id|>
+
+<|start_header_id|>assistant<|end_header_id|>
+"""
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+hf_llm = HuggingFaceEndpoint(
+    endpoint_url=f"{os.environ["YOUR_LLM_ENDPOINT_URL"]}",
+    max_new_tokens=512,
+    top_k=10,
+    top_p=0.95,
+    typical_p=0.95,
+    temperature=0.01,
+    repetition_penalty=1.03,
+    huggingfacehub_api_token=os.environ["HF_TOKEN"]
+)
+hf_embeddings = HuggingFaceEndpointEmbeddings(
+    model=os.environ["YOUR_EMBED_MODEL_URL"],
+    task="feature-extraction",
+    huggingfacehub_api_token=os.environ["HF_TOKEN"],
+)
+
+rag_prompt = PromptTemplate.from_template(RAG_PROMPT_TEMPLATE)
+rag_chain = rag_prompt | hf_llm
+
+def cosine_similarity(phrase_1, phrase_2):
+  vec_1 = hf_embeddings.embed_documents([phrase_1])[0]
+  vec2_2 = hf_embeddings.embed_documents([phrase_2])[0]
+  return np.dot(vec_1, vec2_2) / (norm(vec_1) * norm(vec2_2))
+
+def process_file(file: AskFileResponse):
+    import tempfile
+
+    with tempfile.NamedTemporaryFile(mode="w", delete=False) as tempfile:
+        with open(tempfile.name, "wb") as f:
+            f.write(file.content)
+
+    Loader = PyMuPDFLoader
+
+    loader = Loader(tempfile.name)
+    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
+
+    while files == None:
+        # Async method: This allows the function to pause execution while waiting for the user to upload a file,
+        # without blocking the entire application. It improves responsiveness and scalability.
+        files = await cl.AskFileMessage(
+            content="Please upload a PDF file to begin!",
+            accept=["application/pdf"],
+            max_size_mb=20,
+            timeout=180,
+            max_files=1
+        ).send()
+
+    file = files[0]
+    msg = cl.Message(
+        content=f"Processing `{file.name}`...",
+    )
+    await msg.send()
+    docs = process_file(file)
+
+    # Typical QDrant Client Set-up
+    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(
+        hf_embeddings, store, namespace=hf_embeddings.model
+    )
+
+    # Typical QDrant Vector Store Set-up
+    vectorstore = QdrantVectorStore(
+        client=client,
+        collection_name=collection_name,
+        embedding=cached_embedder)
+    
+    for i in range(0, len(docs), 32):
+        if i == 0:
+            vectorstore = docs.from_documents(docs[i:i+32], hf_embeddings)
+            continue
+        vectorstore.add_documents(docs[i:i+32])
+
+    retriever = vectorstore.as_retriever(search_type="mmr", search_kwargs={"k": 3})
+
+    retrieval_augmented_qa_chain = (
+        {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
+        | RunnablePassthrough.assign(context=itemgetter("context"))
+        | rag_prompt | hf_llm
+    )
+
+    # 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_chain)
+    
+
+### Rename Chains ###
+@cl.author_rename
+def rename(orig_author: str):
+    """ RENAME CODE HERE """
+    rename_dict = {"ChatOpenAI": "the Generator...", "VectorStoreRetriever": "the Retriever..."}
+    return rename_dict.get(orig_author, orig_author)
+
+### On Message Section ###
+@cl.on_message
+async def main(message: cl.Message):
+    """
+    MESSAGE CODE HERE
+    """
+    runnable = cl.user_session.get("chain")
+
+    msg = cl.Message(content="")
+
+    # Async method: Using astream allows for asynchronous streaming of the response,
+    # improving responsiveness and user experience by showing partial results as they become available.
+    async for chunk in runnable.astream(
+        {"question": message.content},
+        config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
+    ):
+        await msg.stream_token(chunk.content)
+
+    await msg.send()

requirements.txt

@@ -0,0 +1,100 @@
+langchain_huggingface==0.0.3
+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