Delete app.py

app.py

@@ -1,128 +0,0 @@
-# -*- coding: utf-8 -*-
-"""app.py
-
-Automatically generated by Colab.
-
-Original file is located at
-    https://colab.research.google.com/drive/1mhabOf4-2l1cLqd8jiKPDx-5NYSCi7gx
-"""
-
-import gradio as gr
-import os
-from typing import List, Optional
-
-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.chains import RetrievalQA
-from langchain.llms.base import LLM
-from groq import Groq
-
-# Ensure Groq API key is set as an environment variable for Hugging Face Spaces compatibility
-# For local testing, you can uncomment and replace with your key, or set it in your environment.
-os.environ["GROQ_API_KEY"] = "YOUR_GROQ_API_KEY" # Replace with your actual API key if not using env var
-
-# --- RAG Pipeline Setup (from your provided code) ---
-
-# Step 1: Load Sample README File
-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
-'''
-
-# Create a dummy file for the loader, as TextLoader expects a file path
-with open("sample_readme.txt", "w") as f:
-    f.write(sample_text)
-
-loader = TextLoader("sample_readme.txt")
-documents = loader.load()
-
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-docs = text_splitter.split_documents(documents)
-
-# Step 2: Create Embeddings & Store in Chroma
-# For Hugging Face Spaces, ensure the model is downloaded and accessible.
-# persist_directory ensures that the vectorstore is saved and can be reloaded.
-embedding = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
-vectorstore = Chroma.from_documents(docs, embedding, persist_directory="rag_chroma_groq")
-
-# Step 3: Define GROQ LLM Wrapper
-class GroqLLM(LLM):
-    model: str = "llama3-8b-8192"
-    # Fetch API key from environment variable
-    api_key: str = os.getenv("GROQ_API_KEY")
-    temperature: float = 0.0
-
-    def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:
-        if not self.api_key:
-            raise ValueError("GROQ_API_KEY environment variable not set.")
-        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 4: Build RAG Pipeline with GROQ
-# Check if GROQ_API_KEY is set before initializing GroqLLM
-if os.getenv("GROQ_API_KEY"):
-    groq_llm = GroqLLM()
-    retriever = vectorstore.as_retriever()
-    qa_chain = RetrievalQA.from_chain_type(
-        llm=groq_llm,
-        retriever=retriever,
-        return_source_documents=True
-    )
-else:
-    qa_chain = None # Set to None if API key is not available
-
-# --- Gradio UI Implementation ---
-
-def rag_query(query: str) -> str:
-    """
-    Function to handle RAG queries through the Gradio interface.
-    """
-    if not qa_chain:
-        return "Error: GROQ_API_KEY is not set. Please set it as an environment variable."
-    try:
-        result = qa_chain({"query": query})
-        answer = result["result"]
-        # Optionally, you can also return source documents if needed
-        # sources = "\n\nSource Documents:\n" + "\n".join([doc.page_content for doc in result["source_documents"]])
-        # return answer + sources
-        return answer
-    except Exception as e:
-        return f"An error occurred: {str(e)}"
-
-# Define the Gradio interface
-iface = gr.Interface(
-    fn=rag_query,
-    inputs=gr.Textbox(lines=2, placeholder="Enter your query here..."),
-    outputs="text",
-    title="RAG Pipeline with GROQ LLaMA3",
-    description="Ask questions about the sample project documentation and get answers from a GROQ-powered RAG system.",
-    allow_flagging="never" # Disable flagging for Hugging Face Spaces
-)
-
-# Launch the Gradio app
-if __name__ == "__main__":
-    iface.launch()