Update app.py

app.py

@@ -1,64 +1,49 @@
+import gradio as gr
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import Chroma
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.document_loaders import TextLoader
+from langchain.document_loaders import PyPDFLoader
 from langchain.chains import RetrievalQA
 from langchain.llms.base import LLM
-
-from typing import List, Optional
 from groq import Groq
-import os
-
-sample_text = '''# Sample Project
-
-This 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.
-
-## Features
-
-- Document embedding
-- Vector similarity search
-- LLM-based QA over documents
-'''
-
+from typing import List, Optional
 
-from langchain.document_loaders import PyPDFLoader
+# Step 1: Load PDF and prepare vector store
 loader = PyPDFLoader("/content/ivas103.pdf")
 documents = loader.load()
 
-
 text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
 docs = text_splitter.split_documents(documents)
 
 embedding = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
 vectorstore = Chroma.from_documents(docs, embedding, persist_directory="rag_chroma_groq")
 
+# Step 2: Define custom LLM class using Groq
 class GroqLLM(LLM):
     model: str = "llama3-8b-8192"
-    api_key: str = "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"  # Replace with your actual API key
+    api_key: str = "your_groq_api_key_here"  # Replace with your key
     temperature: float = 0.7
 
     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"
 
+# Step 3: Create RetrievalQA chain
 retriever = vectorstore.as_retriever()
-groq_llm = GroqLLM(api_key="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")
+groq_llm = GroqLLM(api_key="your_groq_api_key_here")  # Replace with your key
 
 qa_chain = RetrievalQA.from_chain_type(
     llm=groq_llm,
@@ -66,6 +51,20 @@ qa_chain = RetrievalQA.from_chain_type(
     return_source_documents=True
 )
 
-query = "What is a chassis?"
-result = qa_chain({"query": query})
-print("Answer:", result["result"])
+# Step 4: Gradio interface function
+def ask_question(query):
+    result = qa_chain({"query": query})
+    answer = result["result"]
+    sources = "\n\n".join([doc.metadata.get("source", "Unknown") for doc in result["source_documents"]])
+    return f"### Answer:\n{answer}\n\n### Sources:\n{sources}"
+
+# Step 5: Launch Gradio UI
+iface = gr.Interface(
+    fn=ask_question,
+    inputs=gr.Textbox(label="Ask a question", placeholder="e.g., What is a chassis?"),
+    outputs=gr.Markdown(),
+    title="📄 PDF RAG Chatbot (Groq + LangChain)",
+    description="Ask questions based on the content of the PDF file."
+)
+
+iface.launch()