trace

.gitignore

@@ -1 +1,2 @@
-.streamlit
+.streamlit
+test.py

app.py

@@ -1,5 +1,6 @@
 from collections import defaultdict
 import json
+import os
 import re
 
 from langchain_core.documents import Document
@@ -17,8 +18,12 @@ import streamlit as st
 
 
 st.set_page_config(layout="wide", page_title="LegisQA")
-SS = st.session_state
 
+os.environ["LANGCHAIN_API_KEY"] = st.secrets["langchain_api_key"]
+os.environ["LANGCHAIN_TRACING_V2"] = "true"
+os.environ["LANGCHAIN_PROJECT"] = st.secrets["langchain_project"]
+
+SS = st.session_state
 SEED = 292764
 CONGRESS_NUMBERS = [113, 114, 115, 116, 117, 118]
 SPONSOR_PARTIES = ["D", "R", "L", "I"]
@@ -95,13 +100,12 @@ def load_bge_embeddings():
 
 def load_pinecone_vectorstore():
     emb_fn = load_bge_embeddings()
-    pc = Pinecone(api_key=st.secrets["pinecone_api_key"])
-    index = pc.Index(st.secrets["pinecone_index_name"])
     vectorstore = PineconeVectorStore(
-        index=index,
         embedding=emb_fn,
         text_key="text",
         distance_strategy=DistanceStrategy.COSINE,
+        pinecone_api_key=st.secrets["pinecone_api_key"],
+        index_name=st.secrets["pinecone_index_name"],
     )
     return vectorstore
 
@@ -417,16 +421,42 @@ with query_tab:
             search_kwargs={"k": SS["n_ret_docs"], "filter": vs_filter},
         )
         prompt = PromptTemplate.from_template(SS["prompt_template"])
+
+        # # takes in a dict. adds context key with formatted docs
+        # rag_chain_from_docs = (
+        #     RunnablePassthrough.assign(context=(lambda x: format_docs(x["context"])))
+        #     | prompt
+        #     | llm
+        #     | StrOutputParser()
+        # )
+
+        # # takes in a query string.
+        # # passes to retriever and passthru
+        # # assign answer 
+        # rag_chain_with_source = RunnableParallel(
+        #     {"context": retriever, "question": RunnablePassthrough()}
+        # ).assign(answer=rag_chain_from_docs)
+
+
+        # takes in a dict. adds context key with formatted docs
         rag_chain_from_docs = (
             RunnablePassthrough.assign(context=(lambda x: format_docs(x["context"])))
             | prompt
             | llm
             | StrOutputParser()
         )
+
+        # takes in a query string.
+        # passes to retriever and passthru
+        # assign answer 
         rag_chain_with_source = RunnableParallel(
             {"context": retriever, "question": RunnablePassthrough()}
         ).assign(answer=rag_chain_from_docs)
 
+
+
+        print(rag_chain_with_source)
+
         with get_openai_callback() as cb:
             SS["out"] = rag_chain_with_source.invoke(SS["query"])
             SS["cb"] = cb