Update app.py

app.py

@@ -1,64 +1,104 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
+import os
+import tempfile
+import streamlit as st
+from dotenv import load_dotenv
+ 
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Chroma
+from langchain_community.embeddings import BedrockEmbeddings
+from langchain_community.chat_models import BedrockChat
+from langchain.chains import RetrievalQA
+import boto3
+ 
+# Load AWS credentials from .env if available
+load_dotenv()
+ 
+# Setup AWS Bedrock runtime
+bedrock_runtime = boto3.client("bedrock-runtime", region_name="us-east-1")
+ 
+# UI setup
+st.set_page_config(page_title="PDF chatbot", layout="wide")
+st.title("RAG Demo - PDF Q&A")
+ 
+st.markdown("""
+1. **Upload Your Documents**: You can upload multiple PDF files for processing.
+ 
+2. **Ask a Question**: Then ask any question based on the documents' content.
+""")
+ 
+CHROMA_PATH = os.path.join(os.getcwd(), "chroma_db")
+ 
+ 
+def main():
+    st.header("Ask a question")
+ 
+    # Initialize vector store with Amazon Titan Embeddings
+    embeddings = BedrockEmbeddings(
+        client=bedrock_runtime,
+        model_id="amazon.titan-embed-text-v1"
+    )
+    vectorstore = Chroma(
+        persist_directory=CHROMA_PATH,
+        embedding_function=embeddings
+    )
+ 
+    # Sidebar: Upload & Process PDFs
+    with st.sidebar:
+        st.title("Menu:")
+        uploaded_files = st.file_uploader(
+            "Upload PDF files and click Submit",
+            accept_multiple_files=True,
+            key="pdf_uploader"
+        )
+        if st.button("Submit & Process", key="process_button") and uploaded_files:
+            with st.spinner("Processing..."):
+                for uploaded_file in uploaded_files:
+                    try:
+                        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
+                            tmp_file.write(uploaded_file.getvalue())
+                            tmp_path = tmp_file.name
+ 
+                        loader = PyPDFLoader(tmp_path)
+                        pages = loader.load()
+ 
+                        for page in pages:
+                            page.metadata["page_number"] = pages.index(page) + 1
+ 
+                        text_splitter = RecursiveCharacterTextSplitter(
+                            chunk_size=1000,
+                            chunk_overlap=200,
+                            separators=["\n\n", "\n", " ", ""]
+                        )
+                        chunks = text_splitter.split_documents(pages)
+                        os.unlink(tmp_path)
+ 
+                        vectorstore.add_documents(chunks)
+                        vectorstore.persist()
+ 
+                    except Exception as e:
+                        st.error(f"Error processing {uploaded_file.name}: {str(e)}")
+                        continue
+ 
+                st.success("Vector store updated with uploaded documents.")
+ 
+    # Main QA interface
+    user_question = st.text_input("Ask a Question from the PDF Files", key="user_question")
+    if user_question:
+        retriever = vectorstore.as_retriever(search_type='similarity', search_kwargs={'k': 5})
+ 
+        llm = BedrockChat(
+            client=bedrock_runtime,
+            model_id="anthropic.claude-v2",  # or v2:1
+            model_kwargs={"temperature": 0.0}
+        )
+ 
+        chain = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever)
+ 
+        with st.spinner("Generating answer..."):
+            answer = chain.invoke({"query": user_question})
+            st.write("**Reply:**", answer["result"])
+ 
+ 
 if __name__ == "__main__":
-    demo.launch()
+    main()