Create app.py

app.py

@@ -0,0 +1,71 @@
+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 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 langchain.document_loaders import PyPDFLoader
+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")
+
+class GroqLLM(LLM):
+    model: str = "llama3-8b-8192"
+    api_key: str = "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"  # Replace with your actual API 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"
+
+retriever = vectorstore.as_retriever()
+groq_llm = GroqLLM(api_key="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")
+
+qa_chain = RetrievalQA.from_chain_type(
+    llm=groq_llm,
+    retriever=retriever,
+    return_source_documents=True
+)
+
+query = "What is a chassis?"
+result = qa_chain({"query": query})
+print("Answer:", result["result"])