updated langchain related codebase (#7314)

Author: keydunov

examples/langchain/.gitignore

@@ -1,3 +1,4 @@
 .env
+.venv
 __pycache__
 vectorstore.pkl

examples/langchain/streamlit_app.py

@@ -8,20 +8,16 @@
 from dotenv import load_dotenv
 from langchain import OpenAI
 from langchain.embeddings import OpenAIEmbeddings
-from langchain.vectorstores.faiss import FAISS
+from langchain.vectorstores import FAISS
 from langchain.document_loaders import CubeSemanticLoader
 from pathlib import Path
 
 from utils import (
-    create_docs_from_values,
-    create_vectorstore,
-    init_vectorstore,
     check_input,
     log,
     call_sql_api,
     CUBE_SQL_API_PROMPT,
     _NO_ANSWER_TEXT,
-    PROMPT_POSTFIX,
 )
 
 load_dotenv()
@@ -67,7 +63,10 @@ def ingest_cube_meta():
 
 if st.button("Submit", type="primary"):
     check_input(question)
-    vectorstore = init_vectorstore()
+    if not Path("vectorstore.pkl").exists():
+        st.warning("vectorstore.pkl does not exist.")
+    with open("vectorstore.pkl", "rb") as f:
+        vectorstore = pickle.load(f)
 
     # log("Quering vectorstore and building the prompt...")
 

examples/langchain/utils.py

@@ -1,16 +1,10 @@
 import streamlit as st
-import pickle
 import datetime
 import os
 import psycopg2
 
 from dotenv import load_dotenv
-from pathlib import Path
-from typing import List
-from langchain.vectorstores import VectorStore
 from langchain.prompts import PromptTemplate
-from langchain.embeddings import OpenAIEmbeddings
-from langchain.vectorstores.faiss import FAISS
 from langchain.docstore.document import Document
 
 
@@ -30,21 +24,6 @@ def check_input(question: str):
         pass
 
 
-def init_vectorstore() -> VectorStore:
-    vectorstore: VectorStore = None
-    if not Path("vectorstore.pkl").exists():
-        st.warning("vectorstore.pkl does not exist, please run ingest.py first")
-    with open("vectorstore.pkl", "rb") as f:
-        vectorstore = pickle.load(f)
-    return vectorstore
-
-
-def create_vectorstore(documents: List[Document]) -> VectorStore:
-    embeddings = OpenAIEmbeddings()
-    vectorstore = FAISS.from_documents(documents, embeddings)
-    return vectorstore
-
-
 _postgres_prompt = """\
 You are a PostgreSQL expert. Given an input question, create a syntactically correct PostgreSQL query to run and return it as the answer to the input question.
 Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per PostgreSQL.