Update src/streamlit_app.py

src/streamlit_app.py

@@ -30,16 +30,13 @@ with st.container():
     st.markdown("Ask financial questions about ITC Ltd. based on transcript data, powered by AI.")
     st.markdown('</div>', unsafe_allow_html=True)
 
-
-    
-# Load API key securely from Hugging Face secrets
-GOOGLE_API_KEY = st.secrets.get("GOOGLE_API_KEY")
-   
+# Load API key
+GOOGLE_API_KEY = st.secrets.get("genai")
 
 # Initialize Chroma DB
 @st.cache_resource
-def initialize_vectorstore(GOOGLE_API_KEY):
-    embedding = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=GOOGLE_API_KEY)
+def initialize_vectorstore(api_key):
+    embedding = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
     zip_path = "./chroma_db1.zip"
     extract_dir = "chroma_db2"
     if os.path.exists(zip_path):
@@ -47,7 +44,6 @@ def initialize_vectorstore(GOOGLE_API_KEY):
             with zipfile.ZipFile(zip_path, 'r') as zip_ref:
                 zip_ref.extractall(extract_dir)
             vectorstore = Chroma(persist_directory=extract_dir, embedding_function=embedding)
-            vectorstore.persist()
             if vectorstore._collection.count() > 0:
                 return vectorstore
             else:
@@ -58,42 +54,37 @@ def initialize_vectorstore(GOOGLE_API_KEY):
         st.error(f"`chroma_db1.zip` not found at {zip_path}")
     return None
 
-# Initialize vectorstore and retriever
 retriever = None
+vectorstore = None
+llm, parser = None, None
 
-vectorstore = initialize_vectorstore(GOOGLE_API_KEY)
-if vectorstore:
-    retriever = vectorstore.as_retriever(search_type="mmr", search_kwargs={"k": 3, "lambda_mult": 1})
+if GOOGLE_API_KEY:
+    vectorstore = initialize_vectorstore(GOOGLE_API_KEY)
+    if vectorstore:
+        retriever = vectorstore.as_retriever(search_type="mmr", search_kwargs={"k": 3, "lambda_mult": 1})
+    llm = ChatGoogleGenerativeAI(api_key=GOOGLE_API_KEY, model="gemini-1.5-flash", temperature=1)
+    parser = StrOutputParser()
 
 # Prompt template
 prompt = ChatPromptTemplate.from_messages([
     ("system",
      """You are a domain-specific AI financial analyst focused on company-level performance evaluation.
-
 Your task is to analyze and respond to user financial queries strictly based on the provided transcript data: {context}.
-
 Rules:
 1. ONLY extract facts, figures, and insights that are explicitly available in the transcript.
 2. If data is missing or partially available, clearly state: "The required data is not available in the current transcript." Then provide a generic but relevant explanation based on standard financial principles.
 3. Maintain numerical accuracy and avoid interpretation beyond data boundaries.
 4. Prioritize answers relevant to ITC Ltd., but keep response format adaptable to other firms and fiscal years.
 5. Clearly present year-wise or metric-wise insights using bullet points or structured formats if applicable.
-
 Your goals:
 - Ensure 100% fidelity to source transcript.
 - Do not assume or hallucinate missing numbers.
 - Use clear, reproducible reasoning steps (e.g., show which line items support your conclusion).
 - Output should be modular enough to scale across other companies and time periods.
-
-Respond only to this question from the user."""),
-
+Respond only to this question from the user."""
+    ),
     ("human", "{question}")
 ])
-# LLM setup
-llm, parser = None, None
-if GOOGLE_API_KEY:
-    llm = ChatGoogleGenerativeAI(api_key=GOOGLE_API_KEY, model="gemini-1.5-flash", temperature=1)
-    parser = StrOutputParser()
 
 # Helper functions
 def format_docs(docs):