Update app.py

app.py

@@ -3,13 +3,11 @@ import json
 import chromadb
 import numpy as np
 from dotenv import load_dotenv
-from fastapi import FastAPI, HTTPException
-from pydantic import BaseModel
+import gradio as gr
+from groq import Groq
 import torch
 from transformers import AutoTokenizer, AutoModel
-from groq import Groq
-import gradio as gr
-import httpx  # Used to make async HTTP requests to FastAPI
+import logging
 
 # Load environment variables
 load_dotenv()
@@ -29,9 +27,6 @@ if not any(api_keys):
 current_key_index = 0
 client = Groq(api_key=api_keys[current_key_index])
 
-# FastAPI app
-app = FastAPI()
-
 # Define Groq-based model with fallback
 class GroqChatbot:
     def __init__(self, api_keys):
@@ -177,56 +172,21 @@ embedding_store = LocalEmbeddingStore(storage_dir="./chromadb_storage")
 chatbot = GroqChatbot(api_keys=api_keys)
 rag_system = RAGSystem(groq_client=chatbot, embedding_store=embedding_store)
 
-# Pydantic models for API request and response
-class UserInput(BaseModel):
-    input_text: str
-
-class ChatResponse(BaseModel):
-    response: str
-
-@app.get("/")
-async def read_root():
-    return {"message": "Welcome to the Groq and ChromaDB integration API!"}
-
-@app.post("/chat", response_model=ChatResponse)
-async def chat(user_input: UserInput):
-    """Handle chat interactions with Groq and ChromaDB."""
-    ai_response = rag_system.chat_with_rag(user_input.input_text)
-    return ChatResponse(response=ai_response)
-
-@app.post("/embed", response_model=ChatResponse)
-async def embed_text(user_input: UserInput):
-    """Handle text embedding."""
-    embedding = chatbot.text_to_embedding(user_input.input_text)
-    if embedding is not None:
-        return ChatResponse(response="Text embedded successfully.")
-    else:
-        raise HTTPException(status_code=400, detail="Embedding generation failed.")
-
-@app.post("/add_document", response_model=ChatResponse)
-async def add_document(user_input: UserInput):
-    """Add a document embedding to ChromaDB."""
-    embedding = chatbot.text_to_embedding(user_input.input_text)
-    if embedding is not None:
-        doc_id = "sample_document"  # You can generate or pass a doc ID
-        embedding_store.add_embedding(doc_id, embedding, metadata={"source": "user_input"})
-        return ChatResponse(response="Document added to the database.")
-    else:
-        raise HTTPException(status_code=400, detail="Embedding generation failed.")
-
-# Gradio Interface for querying the FastAPI /chat endpoint
-async def gradio_chatbot(input_text: str):
-    async with httpx.AsyncClient() as client:
-        response = await client.post(
-            "http://127.0.0.1:7860/chat",  # FastAPI endpoint
-            json={"input_text": input_text}
-        )
-        response_data = response.json()
-        return response_data["response"]
-
-# Gradio Interface
-iface = gr.Interface(fn=gradio_chatbot, inputs="text", outputs="text")
+# Gradio UI
+def chat_ui(user_input, chat_history):
+    """Handle chat interactions and update history."""
+    if not user_input.strip():
+        return chat_history
+    ai_response = rag_system.chat_with_rag(user_input)
+    chat_history.append((user_input, ai_response))
+    return chat_history
+
+# Gradio interface
+with gr.Blocks() as demo:
+    chat_history = gr.Chatbot(label="Groq Chatbot with RAG", elem_id="chatbox")
+    user_input = gr.Textbox(placeholder="Enter your prompt here...")
+    submit_button = gr.Button("Submit")
+    submit_button.click(chat_ui, inputs=[user_input, chat_history], outputs=chat_history)
 
 if __name__ == "__main__":
-    # Launch the Gradio interface
-    iface.launch()
+    demo.launch()