Delete app-old.py

app-old.py

@@ -1,95 +0,0 @@
-import streamlit as st # for web UI creation 
-from sentence_transformers import SentenceTransformer # this is for embedding queries into dense vectors 
-from pinecone import Pinecone, ServerlessSpec # for accessing pinecone vector DB 
-import os # for readhing environment variable 
-from langchain_huggingface import HuggingFaceEndpoint # for accessing HuggingFace inference endpoint 
-from langchain.prompts import PromptTemplate 
-import firebase_admin # for access to firebase 
-from firebase_admin import credentials, firestore
-
-# === Load .env.local config file ===
-from dotenv import load_dotenv 
-load_dotenv(".env.local")
-
-# === CONFIG ===
-PINECONE_API_KEY = os.getenv("PINECONE_API_KEY")
-PINECONE_ENV = os.getenv("PINECONE_ENV")
-HF_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
-USER_ID = "demo_user"  # static user for testing
-
-# === Firebase Setup ===
-if not firebase_admin._apps:
-    cred = credentials.Certificate("service-account-key.json") 
-    firebase_admin.initialize_app(cred)
-db = firestore.client()
-
-# === Setup Pinecone & Embedding Model ===
-pc = Pinecone(api_key=PINECONE_API_KEY)
-INDEX_NAME = "clinical-trials-rag-vector"
-index = pc.Index(INDEX_NAME)
-
-embed_model = SentenceTransformer("pritamdeka/BioBERT-mnli-snli-scinli-scitail-mednli-stsb") # BioBERT sentence transformer model
-
-# === LLM Part ===
-llm = HuggingFaceEndpoint(
-    endpoint_url="https://bjgtatzbe3uoqewn.us-east-2.aws.endpoints.huggingface.cloud",  # Inference Endpoint Built from Hugging Face. Pay per hour. 
-    huggingfacehub_api_token=os.getenv("HUGGINGFACEHUB_API_TOKEN"),
-    temperature=0.7,
-    max_new_tokens=256
-)
-# prompt template example 
-prompt_template = PromptTemplate.from_template(
-    "Context:\n{context}\n\nQuestion: {question}\nAnswer:"
-)
-
-# === Tabs ===
-tab1, tab2 = st.tabs(["🔍 Ask question related to clinical trial", "⭐ Bookmarked Trials"])
-
-# === TAB 1: Question Part ===
-with tab1:
-    st.title("Clinical Trial Discovery - Ask a Question")
-    user_query = st.text_input("Enter your medical question or condition", "")
-
-    if user_query:
-        with st.spinner("Retrieving relevant trials..."):
-            vec = embed_model.encode(user_query).tolist()
-            results = index.query(vector=vec, top_k=5, include_metadata=True)
-            contexts = [r["metadata"]["text"] for r in results["matches"]]
-            nct_ids = [r["metadata"].get("nct_id", "") for r in results["matches"]]
-
-        joined_context = "\n".join(contexts)
-        prompt = prompt_template.format(context=joined_context, question=user_query)
-
-        with st.spinner("Generating answer..."):
-            answer = llm(prompt)
-        st.subheader("🧠 Answer:")
-        st.write(answer)
-
-        st.markdown("---")
-        st.subheader("📋 Related Clinical Trials")
-
-        for i, match in enumerate(results["matches"]):
-            meta = match["metadata"]
-            nct_id = meta.get("nct_id", f"chunk_{i}")
-            chunk_text = meta.get("text", "")[:400]
-            with st.expander(f"Trial: {nct_id}"):
-                st.write(chunk_text + "...")
-                if st.button(f"⭐ Bookmark {nct_id}", key=f"bookmark_{i}"):
-                    db.collection("Users").document(USER_ID)                      .collection("Bookmarks").document(nct_id).set({
-                          "nct_id": nct_id,
-                          "text": chunk_text
-                      })
-                    st.success(f"Bookmarked {nct_id} to Firestore.")
-
-# === TAB 2: Bookmarked Trials ===
-with tab2:
-    st.title("⭐ Your Bookmarked Trials")
-    docs = db.collection("Users").document(USER_ID).collection("Bookmarks").stream()
-    bookmarks = [doc.to_dict() for doc in docs]
-
-    if not bookmarks:
-        st.info("You haven't bookmarked any trials yet.")
-    else:
-        for b in bookmarks:
-            with st.expander(f"{b['nct_id']}"):
-                st.write(b["text"])