app

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

@@ -2,54 +2,163 @@
 """
 IMPORTS HERE
 """
-# Example Imports (adjust based on actual needs)
+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.chat_models import ChatOpenAI
-from langchain.chains import ConversationChain
-from langchain.prompts import ChatPromptTemplate
-from langchain.schema import StrOutputParser
-from langchain.schema.runnable import Runnable
-from langchain.schema.runnable.config import RunnableConfig
-from typing import cast
+from langchain_core.runnables.config import RunnableConfig
+
+load_dotenv()
 
 ### Global Section ###
 """
 GLOBAL CODE HERE
 """
-# Initialize a language model or chain globally
-llm = ChatOpenAI(temperature=0.9)
-conversation_chain = ConversationChain(llm=llm)
+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"
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+
+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)
+])
+
+chat_model = ChatOpenAI(model="gpt-4o-mini")
+# Typical Embedding Model
+core_embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+
+def process_file(file: AskFileResponse):
+    import tempfile
 
-# Any global variables like API keys, configurations, etc.
-# API_KEY = "your_api_key_here"
+    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 """
-    await cl.Message(content="Welcome! How can I assist you today?").send()
+    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(
+        core_embeddings, store, namespace=core_embeddings.model
+    )
+
+    # Typical QDrant Vector Store Set-up
+    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})
+
+    retrieval_augmented_qa_chain = (
+        {"context": itemgetter("question") | retriever, "question": itemgetter("question")}
+        | RunnablePassthrough.assign(context=itemgetter("context"))
+        | chat_prompt | chat_model
+    )
+
+    # 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):
-    if orig_author == "user":
-        return "You"
-    elif orig_author == "system":
-        return "Assistant"
-    return orig_author
+    """ 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 on_message(message: cl.Message):
-    runnable = cast(Runnable, cl.user_session.get("runnable"))  
+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)
+        await msg.stream_token(chunk.content)
 
     await msg.send()

requirements.txt

@@ -16,10 +16,13 @@ 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
@@ -29,25 +32,44 @@ 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
@@ -60,6 +82,7 @@ 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
@@ -77,15 +100,25 @@ 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