Adding dockerfile

Dockerfile

@@ -1,3 +1,34 @@
+Hugging Face's logo
+Hugging Face
+
+Spaces:
+
+lsy9874205
+/
+assignment15 
+
+like
+0
+App
+Files
+Community
+assignment15
+/
+Dockerfile
+
+lsy9874205's picture
+lsy9874205
+initial files
+d58f81a
+raw
+
+Copy download link
+history
+blame
+contribute
+delete
+
+700 Bytes
 # Get a distribution that has uv already installed
 FROM ghcr.io/astral-sh/uv:python3.13-bookworm-slim
 
@@ -26,4 +57,4 @@ RUN uv sync
 EXPOSE 7860
 
 # Run the app
-CMD ["uv", "run", "chainlit", "run", "app.py", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uv", "run", "chainlit", "run", "app.py", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -19,7 +19,6 @@ from tqdm.asyncio import tqdm
 # ---- ENV VARIABLES ---- # 
 """
 This function will load our environment file (.env) if it is present.
-
 NOTE: Make sure that .env is in your .gitignore file - it is by default, but please ensure it remains there.
 """
 load_dotenv()
@@ -27,14 +26,13 @@ load_dotenv()
 """
 We will load our environment variables here.
 """
-HF_LLM_ENDPOINT = os.environ["HF_LLM_ENDPOINT"]
-HF_EMBED_ENDPOINT = os.environ["HF_EMBED_ENDPOINT"]
-HF_TOKEN = os.environ["HF_TOKEN"]
+HF_LLM_ENDPOINT = os.getenv("HF_LLM_ENDPOINT")
+HF_EMBED_ENDPOINT = os.getenv("HF_EMBED_ENDPOINT")
+HF_TOKEN = os.getenv("HF_TOKEN")
 
 if not all([HF_LLM_ENDPOINT, HF_EMBED_ENDPOINT, HF_TOKEN]):
     raise ValueError("Missing required environment variables. Please check your .env file.")
 
-
 # ---- GLOBAL DECLARATIONS ---- #
 
 # -- RETRIEVAL -- #
@@ -44,16 +42,12 @@ if not all([HF_LLM_ENDPOINT, HF_EMBED_ENDPOINT, HF_TOKEN]):
 3. Load HuggingFace Embeddings (remember to use the URL we set above)
 4. Index Files if they do not exist, otherwise load the vectorstore
 """
-### 1. CREATE TEXT LOADER AND LOAD DOCUMENTS
-### NOTE: PAY ATTENTION TO THE PATH THEY ARE IN. 
-text_loader = TextLoader("./data/paul_graham_essays.txt")
-documents = text_loader.load()
+document_loader = TextLoader("./data/paul_graham_essays.txt")
+documents = document_loader.load()
 
-### 2. CREATE TEXT SPLITTER AND SPLIT DOCUMENTS
 text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=30)
 split_documents = text_splitter.split_documents(documents)
 
-### 3. LOAD HUGGINGFACE EMBEDDINGS
 hf_embeddings = HuggingFaceEndpointEmbeddings(
     model=HF_EMBED_ENDPOINT,
     task="feature-extraction",
@@ -117,29 +111,23 @@ hf_retriever = asyncio.run(run())
 1. Define a String Template
 2. Create a Prompt Template from the String Template
 """
-### 1. DEFINE STRING TEMPLATE
 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|>
 """
 
-### 2. CREATE PROMPT TEMPLATE
 rag_prompt = PromptTemplate.from_template(RAG_PROMPT_TEMPLATE)
 
 # -- GENERATION -- #
 """
 1. Create a HuggingFaceEndpoint for the LLM
 """
-### 1. CREATE HUGGINGFACE ENDPOINT FOR LLM
 hf_llm = HuggingFaceEndpoint(
     endpoint_url=HF_LLM_ENDPOINT,
     max_new_tokens=512,
@@ -154,7 +142,6 @@ hf_llm = HuggingFaceEndpoint(
 def rename(original_author: str):
     """
     This function can be used to rename the 'author' of a message. 
-
     In this case, we're overriding the 'Assistant' author to be 'Paul Graham Essay Bot'.
     """
     rename_dict = {
@@ -166,13 +153,10 @@ def rename(original_author: str):
 async def start_chat():
     """
     This function will be called at the start of every user session. 
-
     We will build our LCEL RAG chain here, and store it in the user session. 
-
     The user session is a dictionary that is unique to each user session, and is stored in the memory of the server.
     """
 
-    ### BUILD LCEL RAG CHAIN THAT ONLY RETURNS TEXT
     lcel_rag_chain = (
         {"context": itemgetter("query") | hf_retriever, "query": itemgetter("query")}
         | rag_prompt | hf_llm
@@ -184,16 +168,14 @@ async def start_chat():
 async def main(message: cl.Message):
     """
     This function will be called every time a message is recieved from a session.
-
     We will use the LCEL RAG chain to generate a response to the user query.
-
     The LCEL RAG chain is stored in the user session, and is unique to each user session - this is why we can access it here.
     """
     lcel_rag_chain = cl.user_session.get("lcel_rag_chain")
 
     msg = cl.Message(content="")
 
-    async for chunk in lcel_rag_chain.astream(
+    for chunk in await cl.make_async(lcel_rag_chain.stream)(
         {"query": message.content},
         config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
     ):

pyproject.toml

@@ -19,4 +19,4 @@ dependencies = [
     "jupyter>=1.1.1",
     "faiss-cpu>=1.10.0",
     "websockets>=15.0",
-]
+]