Upload 2 files

app.py

@@ -0,0 +1,128 @@
+# -*- 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()

requirements.txt

@@ -0,0 +1,9 @@
+langchain
+langchain-community
+openai
+chromadb
+faiss-cpu
+sentence-transformers
+tiktoken
+groq
+gradio