Upload 10 files

Dockerfile

@@ -1,38 +1,38 @@
-# ... existing Dockerfile content ...
-
-# Use an official Python runtime as a parent image
-FROM python:3.12
-
-# Set the working directory in the container
-WORKDIR /app
-
-# Copy the current directory contents into the container at /app
-COPY . /app
-
-# Install system dependencies
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    software-properties-common \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install Python dependencies
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Create the data and db directories with appropriate permissions
-RUN mkdir -p data db && chmod 777 data db
-
-# Make port 8000 available for FastAPI and port 7860 for Streamlit
-EXPOSE 7860
-EXPOSE 8000
-
-# Create a script to run both FastAPI and Streamlit
-RUN echo '#!/bin/bash\n\
-uvicorn main:app --host 0.0.0.0 --port 8000 &\n\
-streamlit run streamlit_app.py --server.port 7860 --server.address 0.0.0.0 --server.enableCORS false\n\
-' > /app/run.sh
-
-RUN chmod +x /app/run.sh
-
-# Run the script when the container launches
+# ... existing Dockerfile content ...
+
+# Use an official Python runtime as a parent image
+FROM python:3.12
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app
+COPY . /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
+    software-properties-common \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Create the data and db directories with appropriate permissions
+RUN mkdir -p data db && chmod 777 data db
+
+# Make port 8000 available for FastAPI and port 7860 for Streamlit
+EXPOSE 8000
+EXPOSE 7860
+
+# Create a script to run both FastAPI and Streamlit
+RUN echo '#!/bin/bash\n\
+uvicorn main:app --host 0.0.0.0 --port 8000 &\n\
+streamlit run streamlit_app.py --server.port 7860 --server.address 0.0.0.0 --server.enableCORS false\n\
+' > /app/run.sh
+
+RUN chmod +x /app/run.sh
+
+# Run the script when the container launches
 CMD ["/app/run.sh"]

app/app.py

@@ -1,9 +1,11 @@
+import os
+from dotenv import load_dotenv
+
 from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate
-from llama_index.llms.huggingface import HuggingFaceInferenceAPI
+from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from llama_index.core import Settings
-import os
-from dotenv import load_dotenv
+
 
 # Load environment variables
 load_dotenv()

huggingface_space.py

@@ -0,0 +1,159 @@
+import os
+from dotenv import load_dotenv
+import shutil
+import uvicorn
+import streamlit as st
+import requests
+import threading
+
+from fastapi import FastAPI, UploadFile, File, HTTPException
+from pydantic import BaseModel, ConfigDict
+
+from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate
+from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_index.core import Settings
+
+
+# Load environment variables
+load_dotenv()
+
+app = FastAPI()
+
+# Configure the Llama index settings
+Settings.llm = HuggingFaceInferenceAPI(
+    model_name="meta-llama/Meta-Llama-3-8B-Instruct",
+    tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
+    context_window=3900,
+    token=os.getenv("HF_TOKEN"),
+    max_new_tokens=1000,
+    generate_kwargs={"temperature": 0.5},
+)
+Settings.embed_model = HuggingFaceEmbedding(
+    model_name="BAAI/bge-small-en-v1.5"
+)
+
+# Define the directory for persistent storage and data
+PERSIST_DIR = "./db"
+DATA_DIR = "data"
+
+# Ensure data directory exists
+os.makedirs(DATA_DIR, exist_ok=True)
+os.makedirs(PERSIST_DIR, exist_ok=True)
+
+class Query(BaseModel):
+    question: str
+
+class DeployedModel(BaseModel):
+    model_id: str
+    model_name: str
+
+    class Config:
+        model_config = ConfigDict(protected_namespaces=())
+
+def data_ingestion():
+    documents = SimpleDirectoryReader(DATA_DIR).load_data()
+    storage_context = StorageContext.from_defaults()
+    index = VectorStoreIndex.from_documents(documents)
+    index.storage_context.persist(persist_dir=PERSIST_DIR)
+
+def handle_query(query):
+    storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
+    index = load_index_from_storage(storage_context)
+    chat_text_qa_msgs = [
+        (
+            "user",
+            """You are Q&A assistant named CHAT-DOC. Your main goal is to provide answers as accurately as possible, based on the instructions and context you have been given. If a question does not match the provided context or is outside the scope of the document, kindly advise the user to ask questions within the context of the document.
+            Context:
+            {context_str}
+            Question:
+            {query_str}
+            """
+        )
+    ]
+    text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)
+    query_engine = index.as_query_engine(text_qa_template=text_qa_template)
+    answer = query_engine.query(query)
+    
+    if hasattr(answer, 'response'):
+        return answer.response
+    elif isinstance(answer, dict) and 'response' in answer:
+        return answer['response']
+    else:
+        return "Sorry, I couldn't find an answer."
+
+@app.post("/upload")
+async def upload_file(file: UploadFile = File(...)):
+    file_extension = os.path.splitext(file.filename)[1].lower()
+    if file_extension not in [".pdf", ".docx", ".txt"]:
+        raise HTTPException(status_code=400, detail="Invalid file type. Only PDF, DOCX, and TXT are allowed.")
+    
+    file_path = os.path.join(DATA_DIR, file.filename)
+    with open(file_path, "wb") as buffer:
+        shutil.copyfileobj(file.file, buffer)
+    
+    data_ingestion()
+    return {"message": "File uploaded and processed successfully"}
+
+@app.post("/query")
+async def query_document(query: Query):
+    if not os.listdir(DATA_DIR):
+        raise HTTPException(status_code=400, detail="No document has been uploaded yet.")
+    
+    response = handle_query(query.question)
+    return {"response": response}
+
+# Streamlit UI
+def streamlit_ui():
+    st.title("Chat with your Document 📄")
+    st.markdown("Chat here👇")
+
+    icons = {"assistant": "🤖", "user": "👤"}
+
+    if 'messages' not in st.session_state:
+        st.session_state.messages = [{'role': 'assistant', "content": 'Hello! Upload a PDF, DOCX, or TXT file and ask me anything about its content.'}]
+
+    for message in st.session_state.messages:
+        with st.chat_message(message['role'], avatar=icons[message['role']]):
+            st.write(message['content'])
+
+    with st.sidebar:
+        st.title("Menu:")
+        uploaded_file = st.file_uploader("Upload your document (PDF, DOCX, TXT)", type=["pdf", "docx", "txt"])
+        if st.button("Submit & Process") and uploaded_file:
+            with st.spinner("Processing..."):
+                files = {"file": (uploaded_file.name, uploaded_file.getvalue(), uploaded_file.type)}
+                response = requests.post("http://localhost:8000/upload", files=files)
+                if response.status_code == 200:
+                    st.success("File uploaded and processed successfully")
+                else:
+                    st.error("Error uploading file")
+
+    user_prompt = st.chat_input("Ask me anything about the content of the document:")
+
+    if user_prompt:
+        st.session_state.messages.append({'role': 'user', "content": user_prompt})
+        with st.chat_message("user", avatar=icons["user"]):
+            st.write(user_prompt)
+
+        # Trigger assistant's response retrieval and update UI
+        with st.spinner("Thinking..."):
+            response = requests.post("http://localhost:8000/query", json={"question": user_prompt})
+            if response.status_code == 200:
+                assistant_response = response.json()["response"]
+                with st.chat_message("assistant", avatar=icons["assistant"]):
+                    st.write(assistant_response)
+                st.session_state.messages.append({'role': 'assistant', "content": assistant_response})
+            else:
+                st.error("Error querying document")
+
+def run_fastapi():
+    uvicorn.run(app, host="0.0.0.0", port=8000)
+
+if __name__ == "__main__":
+    # Start FastAPI in a separate thread
+    fastapi_thread = threading.Thread(target=run_fastapi)
+    fastapi_thread.start()
+
+    # Run Streamlit (this will run in the main thread)
+    streamlit_ui()

main.py

@@ -1,47 +1,48 @@
-import os
-import shutil
-import uvicorn
-
-from pydantic import BaseModel
-from fastapi import FastAPI, File, UploadFile, HTTPException
-from fastapi.middleware.cors import CORSMiddleware
-
-from app.app import data_ingestion, handle_query, DATA_DIR
-
-class Query(BaseModel):
-    question: str
-
-app = FastAPI()
-
-app.add_middleware(
-       CORSMiddleware,
-       allow_origins=["*"],  # Adjust this to your needs
-       allow_credentials=True,
-       allow_methods=["*"],
-       allow_headers=["*"],
-   )
-
-@app.post("/upload")
-async def upload_file(file: UploadFile = File(...)):
-    print(f"Received file: {file.filename}")
-    file_extension = os.path.splitext(file.filename)[1].lower()
-    if file_extension not in [".pdf", ".docx", ".txt"]:
-        raise HTTPException(status_code=400, detail="Invalid file type. Only PDF, DOCX, and TXT are allowed.")
-    
-    file_path = os.path.join(DATA_DIR, file.filename)
-    with open(file_path, "wb") as buffer:
-        shutil.copyfileobj(file.file, buffer)
-    
-    data_ingestion()
-    return {"message": "File uploaded and processed successfully"}
-
-@app.post("/query")
-async def query_document(query: Query):
-    if not os.listdir(DATA_DIR):
-        raise HTTPException(status_code=400, detail="No document has been uploaded yet.")
-    
-    response = handle_query(query.question)
-    return {"response": response}
-
-if __name__ == "__main__":
+import os
+import shutil
+import uvicorn
+
+from pydantic import BaseModel
+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+
+from app.app import data_ingestion, handle_query, DATA_DIR
+
+
+class Query(BaseModel):
+    question: str
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Change this to your frontend's URL in production
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+@app.post("/upload")
+async def upload_file(file: UploadFile = File(...)):
+    print(f"Received file: {file.filename}")  # Log the filename
+    file_extension = os.path.splitext(file.filename)[1].lower()
+    if file_extension not in [".pdf", ".docx", ".txt"]:
+        raise HTTPException(status_code=400, detail="Invalid file type. Only PDF, DOCX, and TXT are allowed.")
+    
+    file_path = os.path.join(DATA_DIR, file.filename)
+    with open(file_path, "wb") as buffer:
+        shutil.copyfileobj(file.file, buffer)
+    
+    data_ingestion()
+    return {"message": "File uploaded and processed successfully"}
+
+@app.post("/query")
+async def query_document(query: Query):
+    if not os.listdir(DATA_DIR):
+        raise HTTPException(status_code=400, detail="No document has been uploaded yet.")
+    
+    response = handle_query(query.question)
+    return {"response": response}
+
+if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=8000)

requirements.txt

@@ -2,10 +2,10 @@ streamlit
 python-dotenv
 llama-index
 llama-index-embeddings-huggingface
-llama-index-llms-huggingface
 gradio==3.50
 docx2txt
 tf-keras
 fastapi
 pydantic
 uvicorn
+llama_index.llms.huggingface_api