Update app.py

app.py

@@ -1,80 +1,50 @@
 import os
-from typing import List, Optional
-
+import gradio as gr
 from langchain_community.document_loaders import TextLoader
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.vectorstores import Chroma
 from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.vectorstores import Chroma
 from langchain.chains import RetrievalQA
-from langchain.llms.base import LLM
-from groq import Groq
-import gradio as gr
-
-# ✅ Create sample file if missing
-if not os.path.exists("sample_readme.txt"):
-    with open("sample_readme.txt", "w") as f:
-        f.write(
-            "# Sample Project\n\nThis project demonstrates an example of a LangChain-powered RAG pipeline. "
-            "It uses FAISS for vector search and a GROQ-hosted LLaMA3 model for response generation.\n\n"
-            "## Features\n- Document embedding\n- Vector similarity search\n- LLM-based QA over documents"
-        )
+from langchain_groq import ChatGroq
 
-# Load & split
+# Load documents
 loader = TextLoader("sample_readme.txt")
 documents = loader.load()
+
+# Split into chunks
 text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
 docs = text_splitter.split_documents(documents)
 
-# Embed & store vectors
+# Create embeddings
 embedding = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+
+# Vector DB
 vectorstore = Chroma.from_documents(docs, embedding, persist_directory="rag_chroma_groq")
+retriever = vectorstore.as_retriever()
 
 # Groq LLM
-class GroqLLM(LLM):
-    model: str = "llama3-8b-8192"
-    api_key: str = os.environ.get("GROQ_API_KEY")
-    temperature: float = 0.0
-
-    def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:
-        client = Groq(api_key=self.api_key)
-        messages = [
-            {"role": "system", "content": "You are a helpful assistant."},
-            {"role": "user", "content": prompt}
-        ]
-        response = client.chat.completions.create(
-            model=self.model,
-            messages=messages,
-            temperature=self.temperature,
-        )
-        return response.choices[0].message.content
-
-    @property
-    def _llm_type(self) -> str:
-        return "groq-llm"
+groq_llm = ChatGroq(api_key=os.getenv("GROQ_API_KEY"), model_name="llama3-70b-8192")
 
-# QA setup
-retriever = vectorstore.as_retriever()
-groq_llm = GroqLLM()
+# RAG chain
 qa_chain = RetrievalQA.from_chain_type(
     llm=groq_llm,
     retriever=retriever,
-    return_source_documents=True
+    return_source_documents=False
 )
 
+# Chat function
+def chatbot_interface(user_query):
+    result = qa_chain({"query": user_query})
+    return result["result"]
+
 # Gradio UI
-def ask_question(query):
-    response = qa_chain(query)
-    answer = response["result"]
-    sources = "\n".join(
-        [doc.metadata.get("source", "sample_readme.txt") for doc in response["source_documents"]]
-    )
-    return f"### Answer:\n{answer}\n\n### Sources:\n{sources}"
+iface = gr.Interface(
+    fn=chatbot_interface,
+    inputs=gr.Textbox(label="Ask a question about the document"),
+    outputs=gr.Textbox(label="Answer"),
+    title="RAG Chatbot with Groq + LangChain",
+    description="Ask questions about sample_readme.txt using Groq LLM"
+)
 
-gr.Interface(
-    fn=ask_question,
-    inputs=gr.Textbox(label="Ask something about the README"),
-    outputs=gr.Markdown(),
-    title="📄 RAG Chatbot with Groq LLaMA3",
-    description="Ask questions about a README file using a LangChain + Groq LLaMA3-powered chatbot.",
-    theme="soft"
-).launch()
+if __name__ == "__main__":
+    iface.launch()