Update app.py

app.py

@@ -1,8 +1,7 @@
 import streamlit as st
 import os
 import requests
-import tempfile
-import chromadb  
+import chromadb
 from langchain.document_loaders import PDFPlumberLoader
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain_experimental.text_splitter import SemanticChunker
@@ -14,13 +13,16 @@ from prompts import rag_prompt, relevancy_prompt, relevant_context_picker_prompt
 
 # ----------------- Streamlit UI Setup -----------------
 st.set_page_config(page_title="Blah", layout="wide")
-st.image("https://huggingface.co/front/assets/huggingface_logo-noborder.svg", width=150)  
+st.image("https://huggingface.co/front/assets/huggingface_logo-noborder.svg", width=150)
 st.title("Blah-1")
 
-
 # ----------------- API Keys -----------------
 os.environ["GROQ_API_KEY"] = st.secrets.get("GROQ_API_KEY", "")
 
+# ----------------- Ensure Vector Store Directory Exists -----------------
+if not os.path.exists("./chroma_langchain_db"):
+    os.makedirs("./chroma_langchain_db")
+
 # ----------------- Clear ChromaDB Cache -----------------
 chromadb.api.client.SharedSystemClient.clear_system_cache()
 
@@ -36,10 +38,14 @@ if "processed_chunks" not in st.session_state:
 if "vector_store" not in st.session_state:
     st.session_state.vector_store = None
 
-# ----------------- Load Models -----------------
+# ----------------- Load Models -------------------
 llm_judge = ChatGroq(model="deepseek-r1-distill-llama-70b")
 rag_llm = ChatGroq(model="mixtral-8x7b-32768")
 
+# Enable verbose logging for debugging
+llm_judge.verbose = True
+rag_llm.verbose = True
+
 # ----------------- PDF Selection (Upload or URL) -----------------
 st.sidebar.subheader("📂 PDF Selection")
 pdf_source = st.radio("Choose a PDF source:", ["Upload a PDF file", "Enter a PDF URL"], index=0, horizontal=True)
@@ -79,7 +85,7 @@ if not st.session_state.pdf_loaded and "pdf_path" in st.session_state:
         loader = PDFPlumberLoader(st.session_state.pdf_path)
         docs = loader.load()
 
-        # Embedding Model
+        # Embedding Model (HF on CPU)
         model_name = "nomic-ai/modernbert-embed-base"
         embedding_model = HuggingFaceEmbeddings(model_name=model_name, model_kwargs={"device": "cpu"})
 
@@ -137,15 +143,15 @@ if query:
         final_output = context_management_chain.invoke({"context": context, "retriever_query": query, "query": query})
         st.success("✅ Full pipeline executed successfully!")
 
-    # ----------------- Display All Outputs -----------------
-    st.subheader("🟥 Context Relevancy Evaluation")
+    # ----------------- Display All Outputs (Formatted) -----------------
+    st.markdown("### 🟥 Context Relevancy Evaluation")
     st.json(final_output["relevancy_response"])
 
-    st.subheader("🟦 Picked Relevant Contexts")
+    st.markdown("### 🟦 Picked Relevant Contexts")
     st.json(final_output["context_number"])
 
-    st.subheader("🟥 Extracted Relevant Contexts")
+    st.markdown("### 🟥 Extracted Relevant Contexts")
     st.json(final_output["relevant_contexts"])
 
-    st.subheader("🟥 RAG Final Response")
+    st.markdown("## 🟥 RAG Final Response")
     st.write(final_output["final_response"])