Update app.py

app.py

@@ -18,6 +18,7 @@ st.title("Blah-1")
 
 # ----------------- API Keys -----------------
 os.environ["GROQ_API_KEY"] = st.secrets.get("GROQ_API_KEY", "")
+os.environ["HF_TOKEN"] = st.secrets.get("HF_TOKEN", "")
 
 # ----------------- Clear ChromaDB Cache -----------------
 chromadb.api.client.SharedSystemClient.clear_system_cache()
@@ -117,42 +118,39 @@ if query:
         context = [d.page_content for d in retrieved_docs]
         st.success("✅ Context retrieved successfully!")
 
-    # ----------------- Full SequentialChain Execution -----------------
-    with st.spinner("🔄 Running full pipeline..."):
-        final_output = SequentialChain(
-            chains=[
-                LLMChain(llm=llm_judge, prompt=PromptTemplate(input_variables=["retriever_query", "context"], template=relevancy_prompt), output_key="relevancy_response"),
-                LLMChain(llm=llm_judge, prompt=PromptTemplate(input_variables=["relevancy_response"], template=relevant_context_picker_prompt), output_key="context_number"),
-                LLMChain(llm=llm_judge, prompt=PromptTemplate(input_variables=["context_number", "context"], template=response_synth), output_key="relevant_contexts"),
-                LLMChain(llm=rag_llm, prompt=PromptTemplate(input_variables=["query", "context"], template=rag_prompt), output_key="final_response")
-            ],
-            input_variables=["context", "retriever_query", "query"],
-            output_variables=["relevancy_response", "context_number", "relevant_contexts", "final_response"]
-        ).invoke({"context": context, "retriever_query": query, "query": query})
+    # ----------------- Run Individual Chains Explicitly -----------------
+    context_relevancy_chain = LLMChain(llm=llm_judge, prompt=PromptTemplate(input_variables=["retriever_query", "context"], template=relevancy_prompt), output_key="relevancy_response")
+    relevant_context_chain = LLMChain(llm=llm_judge, prompt=PromptTemplate(input_variables=["relevancy_response"], template=relevant_context_picker_prompt), output_key="context_number")
+    relevant_contexts_chain = LLMChain(llm=llm_judge, prompt=PromptTemplate(input_variables=["context_number", "context"], template=response_synth), output_key="relevant_contexts")
+    response_chain = LLMChain(llm=rag_llm, prompt=PromptTemplate(input_variables=["query", "context"], template=rag_prompt), output_key="final_response")
+
+    response_crisis = context_relevancy_chain.invoke({"context": context, "retriever_query": query})
+    relevant_response = relevant_context_chain.invoke({"relevancy_response": response_crisis["relevancy_response"]})
+    contexts = relevant_contexts_chain.invoke({"context_number": relevant_response["context_number"], "context": context})
+    final_response = response_chain.invoke({"query": query, "context": contexts["relevant_contexts"]})
 
     # ----------------- Display All Outputs -----------------
     st.markdown("### 🟥 Context Relevancy Evaluation")
-    st.json(final_output["relevancy_response"])
+    st.json(response_crisis["relevancy_response"])
 
     st.markdown("### 🟦 Picked Relevant Contexts")
-    st.json(final_output["context_number"])
+    st.json(relevant_response["context_number"])
 
     st.markdown("### 🟥 Extracted Relevant Contexts")
-    st.json(final_output["relevant_contexts"])
+    st.json(contexts["relevant_contexts"])
 
     st.markdown("## 🟥 RAG Final Response")
-    st.write(final_output["final_response"])
+    st.write(final_response["final_response"])
 
-    # ----------------- Streamlit-Friendly Debugging (Replacing print statements) -----------------
-    st.markdown("### Debug Logs:")
-    st.text("\n-------- 🟥 Context Relevancy Evaluation Statement 🟥 --------\n")
-    st.json(final_output["relevancy_response"])
+    # ----------------- Debugging Output -----------------
+    st.text("\n-------- 🟥 context_relevancy_evaluation_chain Statement 🟥 --------\n")
+    st.json(response_crisis["relevancy_response"])
 
-    st.text("\n-------- 🟦 Picked Relevant Context Statement 🟦 --------\n")
-    st.json(final_output["context_number"])
+    st.text("\n-------- 🟦 pick_relevant_context_chain Statement 🟦 --------\n")
+    st.json(relevant_response["context_number"])
 
-    st.text("\n-------- 🟥 Relevant Contexts Statement 🟥 --------\n")
-    st.json(final_output["relevant_contexts"])
+    st.text("\n-------- 🟥 relevant_contexts_chain Statement 🟥 --------\n")
+    st.json(contexts["relevant_contexts"])
 
-    st.text("\n-------- 🟥 RAG Response Statement 🟥 --------\n")
-    st.write(final_output["final_response"])
+    st.text("\n-------- 🟥 Rag Response Statement 🟥 --------\n")
+    st.write(final_response["final_response"])