Create app.py

app.py

@@ -0,0 +1,61 @@
+# app.py
+
+import os
+from groq import Groq
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+import gradio as gr
+
+# Get GROQ_API_KEY from env
+groq_api_key = os.environ.get("GROQ_API_KEY")
+groq_client = Groq(api_key=groq_api_key)
+
+# Load and embed documents
+def load_documents_and_create_vectorstore():
+    docs = []
+    for file in ["documents/ASTM1.pdf", "documents/ASTM2.pdf"]:
+        loader = PyPDFLoader(file)
+        docs.extend(loader.load())
+
+    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    chunks = splitter.split_documents(docs)
+
+    embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+    vectorstore = FAISS.from_documents(chunks, embeddings)
+
+    return vectorstore
+
+vectorstore = load_documents_and_create_vectorstore()
+
+# RAG: Ask question using context + Groq
+def ask_question(question):
+    retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
+    docs = retriever.get_relevant_documents(question)
+
+    context = "\n".join([doc.page_content for doc in docs])
+
+    prompt = f"""You are a helpful Civil Engineering assistant. Use the ASTM standard context below to answer:
+
+    Context:
+    {context}
+
+    Question: {question}
+    Answer:"""
+
+    completion = groq_client.chat.completions.create(
+        messages=[{"role": "user", "content": prompt}],
+        model="llama-3.3-70b-versatile"
+    )
+
+    return completion.choices[0].message.content
+
+# Gradio UI
+gr.Interface(
+    fn=ask_question,
+    inputs=gr.Textbox(label="Ask a Civil Engineering Question (based on ASTM)"),
+    outputs=gr.Textbox(label="Answer"),
+    title="Civil Engineering RAG Assistant",
+    description="Ask any question about ASTM Civil Engineering Standards"
+).launch()