Update app.py

app.py

@@ -1,63 +1,78 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import chainlit as cl
+from langchain_openai import ChatOpenAI
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import Chroma
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.chains import ConversationalRetrievalChain
+from langchain_community.chat_message_histories import ChatMessageHistory
+from langchain.memory import ConversationBufferMemory
+from langchain_core.prompts import PromptTemplate
 
+# Your API key
+open_ai_key = "sk-proj-DQPYy7NQXLkgtJDLzrijT3BlbkFJuPuWnU33xKyKxgLQauKO"
+
+llm = ChatOpenAI(api_key=open_ai_key)
+
+template = """Use the following pieces of information to answer the user's question.
+If you don't know the answer, just say that you don't know, don't try to make up an answer.
+
+Context: {context}
+Question: {question}
+
+Only return the helpful answer below and nothing else.
+Helpful answer:
 """
-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")
 
+prompt = PromptTemplate(template=template, input_variables=["context", "question"])
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def process_pdf_and_ask_question(pdf_file, question):
+    # Load and process the PDF
+    loader = PyPDFLoader(pdf_file.name)
+    pdf_data = loader.load()
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Split the text into chunks
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    docs = text_splitter.split_documents(pdf_data)
 
-    messages.append({"role": "user", "content": message})
+    # Create a Chroma vector store
+    embeddings = HuggingFaceEmbeddings(model_name="embaas/sentence-transformers-multilingual-e5-base")
+    db = Chroma.from_documents(docs, embeddings)
 
-    response = ""
+    # Initialize message history for conversation
+    message_history = ChatMessageHistory()
 
-    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
+    # Memory for conversational context
+    memory = ConversationBufferMemory(
+        memory_key="chat_history",
+        output_key="answer",
+        chat_memory=message_history,
+        return_messages=True,
+    )
 
-        response += token
-        yield response
+    # Create a chain that uses the Chroma vector store
+    chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        chain_type="stuff",
+        retriever=db.as_retriever(),
+        memory=memory,
+        return_source_documents=False,
+        combine_docs_chain_kwargs={'prompt': prompt}
+    )
 
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+    # Process the question
+    res = chain({"input": question})
+    return res["answer"]
+
+def gradio_interface(pdf, question):
+    return process_pdf_and_ask_question(pdf, question)
+
+# Gradio interface
+gr.Interface(
+    fn=gradio_interface,
+    inputs=[gr.inputs.File(file_count="single", type="file"), gr.inputs.Textbox(lines=2, placeholder="Ask a question...")],
+    outputs="text",
+    title="PDF Q&A",
+    description="Upload a PDF and ask questions about it.",
+).launch()