Update app.py

app.py

@@ -1,7 +1,8 @@
 import os
 import gradio as gr
+import traceback
 
-# LangChain (CLASSIC / STABLE)
+# ---------------- LangChain (STABLE 0.1.x) ----------------
 from langchain.chains import ConversationalRetrievalChain
 from langchain.memory import ConversationBufferMemory
 from langchain.prompts import PromptTemplate
@@ -20,20 +21,18 @@ from langchain_community.document_loaders import (
 )
 from langchain_community.retrievers import BM25Retriever
 
-# Text splitters
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 
-# --------------------------------------------------
-# API KEY
-# --------------------------------------------------
+# ---------------- CONFIG ----------------
 GROQ_API_KEY = os.getenv("GROQ_API")
 
-STRICT_PROMPT_TEMPLATE = """You are a strict document-based assistant.
-Use ONLY the provided context.
+STRICT_PROMPT = PromptTemplate(
+    template="""
+You are a strict document-based assistant.
 
 Rules:
-1. Do not use outside knowledge.
-2. If answer not found, say:
+1. ONLY use the provided context.
+2. If the answer is not in the context, say:
 "I'm sorry, but the provided documents do not contain information to answer this question."
 
 Context:
@@ -42,16 +41,11 @@ Context:
 Question: {question}
 
 Answer:
-"""
-
-STRICT_PROMPT = PromptTemplate(
-    template=STRICT_PROMPT_TEMPLATE,
+""",
     input_variables=["context", "question"]
 )
 
-# --------------------------------------------------
-# LOAD FILES
-# --------------------------------------------------
+# ---------------- FILE LOADER ----------------
 def load_any(path: str):
     path = path.lower()
     if path.endswith(".pdf"):
@@ -62,79 +56,84 @@ def load_any(path: str):
         return Docx2txtLoader(path).load()
     return []
 
-# --------------------------------------------------
-# BUILD RAG
-# --------------------------------------------------
+# ---------------- BUILD CHAIN ----------------
 def process_files(files, response_length):
-    if not files or not GROQ_API_KEY:
-        return None, "⚠️ Missing files or GROQ_API key"
-
-    docs = []
-    for f in files:
-        docs.extend(load_any(f.name))
-
-    splitter = RecursiveCharacterTextSplitter(
-        chunk_size=800,
-        chunk_overlap=100
-    )
-    chunks = splitter.split_documents(docs)
-
-    embeddings = HuggingFaceEmbeddings(
-        model_name="sentence-transformers/all-MiniLM-L6-v2"
-    )
-
-    faiss_db = FAISS.from_documents(chunks, embeddings)
-    faiss_retriever = faiss_db.as_retriever(search_kwargs={"k": 3})
-
-    bm25 = BM25Retriever.from_documents(chunks)
-    bm25.k = 3
-
-    retriever = EnsembleRetriever(
-        retrievers=[faiss_retriever, bm25],
-        weights=[0.5, 0.5]
-    )
-
-    llm = ChatGroq(
-        groq_api_key=GROQ_API_KEY,
-        model="llama-3.3-70b-versatile",
-        temperature=0,
-        max_tokens=int(response_length)
-    )
-
-    memory = ConversationBufferMemory(
-        memory_key="chat_history",
-        return_messages=True,
-        output_key="answer"
-    )
-
-    chain = ConversationalRetrievalChain.from_llm(
-        llm=llm,
-        retriever=retriever,
-        memory=memory,
-        combine_docs_chain_kwargs={"prompt": STRICT_PROMPT},
-        return_source_documents=True,
-        output_key="answer"
-    )
-
-    return chain, "✅ Chatbot built successfully"
-
-# --------------------------------------------------
-# CHAT
-# --------------------------------------------------
+    if not files:
+        return None, "❌ No files uploaded"
+    if not GROQ_API_KEY:
+        return None, "❌ GROQ_API secret not set"
+
+    try:
+        docs = []
+        for f in files:
+            docs.extend(load_any(f.path))  # HF SAFE
+
+        splitter = RecursiveCharacterTextSplitter(
+            chunk_size=800,
+            chunk_overlap=100
+        )
+        chunks = splitter.split_documents(docs)
+
+        embeddings = HuggingFaceEmbeddings(
+            model_name="sentence-transformers/all-MiniLM-L6-v2"
+        )
+
+        faiss_db = FAISS.from_documents(chunks, embeddings)
+        faiss_retriever = faiss_db.as_retriever(search_kwargs={"k": 3})
+
+        bm25 = BM25Retriever.from_documents(chunks)
+        bm25.k = 3
+
+        retriever = EnsembleRetriever(
+            retrievers=[faiss_retriever, bm25],
+            weights=[0.5, 0.5]
+        )
+
+        llm = ChatGroq(
+            groq_api_key=GROQ_API_KEY,
+            model="llama-3.3-70b-versatile",
+            temperature=0,
+            max_tokens=int(response_length)
+        )
+
+        memory = ConversationBufferMemory(
+            memory_key="chat_history",
+            return_messages=True,
+            output_key="answer"
+        )
+
+        chain = ConversationalRetrievalChain.from_llm(
+            llm=llm,
+            retriever=retriever,
+            memory=memory,
+            combine_docs_chain_kwargs={"prompt": STRICT_PROMPT},
+            return_source_documents=True,
+            output_key="answer"
+        )
+
+        return chain, "✅ Chatbot built successfully"
+
+    except Exception as e:
+        traceback.print_exc()
+        return None, f"❌ {repr(e)}"
+
+# ---------------- CHAT ----------------
 def chat_function(message, history, chain):
     if chain is None:
         return "⚠️ Build the chatbot first"
 
-    res = chain.invoke({
+    result = chain.invoke({
         "question": message,
         "chat_history": history
     })
 
-    answer = res["answer"]
+    answer = result["answer"]
 
     sources = {
-        os.path.basename(d.metadata.get("source", "unknown"))
-        for d in res.get("source_documents", [])
+        os.path.basename(
+            d.metadata.get("source", d.metadata.get("file_path", "unknown"))
+        )
+        for d in result.get("source_documents", [])
     }
 
     if sources:
@@ -142,20 +141,18 @@ def chat_function(message, history, chain):
 
     return answer
 
-# --------------------------------------------------
-# UI
-# --------------------------------------------------
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🛡️ Strict Hybrid Multi-RAG")
+# ---------------- UI ----------------
+with gr.Blocks() as demo:
+    gr.Markdown("# 🛡️ Strict Hybrid Multi-RAG (HF-Safe)")
 
     chain_state = gr.State(None)
 
     with gr.Row():
         with gr.Column(scale=1):
-            files = gr.File(file_count="multiple")
-            tokens = gr.Slider(100, 4000, 1000, step=100)
+            files = gr.File(file_count="multiple", label="Upload Documents")
+            tokens = gr.Slider(100, 4000, value=1000, step=100, label="Max Tokens")
             build = gr.Button("Build Chatbot", variant="primary")
-            status = gr.Textbox(interactive=False)
+            status = gr.Textbox(label="Status", interactive=False)
 
         with gr.Column(scale=2):
             gr.ChatInterface(
@@ -170,4 +167,4 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(theme=gr.themes.Soft())