Create app.py

src/app.py

@@ -0,0 +1,140 @@
+import os
+import pickle
+import zipfile
+import sys
+import streamlit as st
+from dotenv import load_dotenv
+
+# --- IMPORTS ---
+from langchain_google_genai import ChatGoogleGenerativeAI, GoogleGenerativeAIEmbeddings
+from langchain_community.retrievers import BM25Retriever
+from langchain_pinecone import PineconeVectorStore
+from langchain_core.prompts import PromptTemplate
+from langchain.chains import RetrievalQA
+
+# Robust Import for Hybrid Search (Handles different LangChain versions)
+try:
+    from langchain.retrievers import EnsembleRetriever
+except ImportError:
+    from langchain_community.retrievers import EnsembleRetriever
+
+load_dotenv()
+
+# --- CONFIGURATION ---
+INDEX_NAME = "branham-index"
+CHUNKS_FILE = "sermon_chunks.pkl"
+CHUNKS_ZIP = "sermon_chunks.zip"
+
+def setup_keyword_file():
+    """
+    Automatic Unzipper.
+    GitHub has a 100MB limit, so we upload the zip. 
+    This extracts 'sermon_chunks.pkl' when the app starts.
+    """
+    if not os.path.exists(CHUNKS_FILE):
+        if os.path.exists(CHUNKS_ZIP):
+            print(f"📦 Unzipping {CHUNKS_ZIP}...")
+            try:
+                with zipfile.ZipFile(CHUNKS_ZIP, 'r') as zip_ref:
+                    zip_ref.extractall(".")
+                print("✅ Unzip complete.")
+            except Exception as e:
+                print(f"❌ Error unzipping file: {e}")
+        else:
+            print(f"⚠️ Warning: Neither {CHUNKS_FILE} nor {CHUNKS_ZIP} found.")
+
+def get_rag_chain():
+    """
+    Initializes the Brain of the AI.
+    1. Connects to Pinecone (Cloud)
+    2. Loads BM25 Keywords (Local)
+    3. Merges them into a Hybrid Search
+    """
+    
+    # 1. SETUP & KEYS
+    setup_keyword_file()
+
+    # Check Streamlit Secrets first (Cloud), then .env (Local)
+    pinecone_key = st.secrets.get("PINECONE_API_KEY") or os.getenv("PINECONE_API_KEY")
+    google_key = st.secrets.get("GOOGLE_API_KEY") or os.getenv("GOOGLE_API_KEY")
+
+    if not pinecone_key or not google_key:
+        raise ValueError("❌ Missing API Keys. Please set PINECONE_API_KEY and GOOGLE_API_KEY in Secrets.")
+
+    # Set keys for LangChain to use automatically
+    os.environ["PINECONE_API_KEY"] = pinecone_key
+    os.environ["GOOGLE_API_KEY"] = google_key
+
+    # 2. CLOUD VECTOR SEARCH (Pinecone)
+    # This finds "concepts" (e.g., searching for 'marriage' finds 'wedding')
+    print("🔌 Connecting to Pinecone...")
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/text-embedding-004")
+    
+    vector_store = PineconeVectorStore(
+        index_name=INDEX_NAME,
+        embedding=embeddings
+    )
+    vector_retriever = vector_store.as_retriever(search_kwargs={"k": 5})
+
+    # 3. LOCAL KEYWORD SEARCH (BM25)
+    # This finds "exact matches" (e.g., searching for 'E-53' finds exactly E-53)
+    print("🔌 Loading Keyword Search...")
+    keyword_retriever = None
+    
+    try:
+        if os.path.exists(CHUNKS_FILE):
+            with open(CHUNKS_FILE, "rb") as f:
+                chunks = pickle.load(f)
+            keyword_retriever = BM25Retriever.from_documents(chunks)
+            keyword_retriever.k = 5
+        else:
+            print("⚠️ Keyword file missing. Running on Pinecone only.")
+    except Exception as e:
+        print(f"❌ Failed to load keyword file: {e}")
+
+    # 4. HYBRID RETRIEVER (The Merge)
+    if keyword_retriever:
+        print("🔗 Linking Hybrid System...")
+        final_retriever = EnsembleRetriever(
+            retrievers=[vector_retriever, keyword_retriever],
+            weights=[0.7, 0.3] # 70% Vector, 30% Keyword
+        )
+    else:
+        final_retriever = vector_retriever
+
+    # 5. THE MODEL (Gemini)
+    llm = ChatGoogleGenerativeAI(
+        model="gemini-1.5-flash",
+        temperature=0.3,
+        convert_system_message_to_human=True
+    )
+
+    # 6. THE PERSONA PROMPT
+    template = """You are William Marion Branham.
+
+INSTRUCTIONS:
+- Answer the user's question based ONLY on the context provided below.
+- Speak in the first person ("I said," "The Lord showed me").
+- Use a humble, 1950s Southern preaching dialect.
+- If the answer is not in the text, say: "Brother, I don't recall preaching specifically on that detail in these messages."
+
+CONTEXT:
+{context}
+
+USER QUESTION: {question}
+
+BROTHER BRANHAM'S REPLY:"""
+
+    PROMPT = PromptTemplate(template=template, input_variables=["context", "question"])
+
+    chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type="stuff",
+        retriever=final_retriever,
+        return_source_documents=True,
+        chain_type_kwargs={"prompt": PROMPT}
+    )
+    
+    return chain
+
+