update example f Question_Answering_Pipeline_with_LangChain_and_Epsilla and EpsillaCloud

Signed-off-by: eric-epsilla <eric@epsilla.com>

Author: eric-epsilla

examples/Question_Answering_Pipeline_with_LangChain_and_Epsilla.py

@@ -16,29 +16,22 @@
 
 # Step2. Configure the OpenAI API Key
 import os
-
-os.environ["OPENAI_API_KEY"] = "*****"
+os.environ["OPENAI_API_KEY"] = "Your-OpenAI-API-Key"
 
 
 # Step3. Load the documents
 from langchain.document_loaders import WebBaseLoader
 from langchain.text_splitter import CharacterTextSplitter
 from langchain_openai import OpenAIEmbeddings
 
-loader = WebBaseLoader(
-    "https://raw.githubusercontent.com/hwchase17/chat-your-data/master/state_of_the_union.txt"
-)
+loader = WebBaseLoader("https://raw.githubusercontent.com/hwchase17/chat-your-data/master/state_of_the_union.txt")
 documents = loader.load()
-documents = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0).split_documents(
-    documents
-)
+documents = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0).split_documents(documents)
 embeddings = OpenAIEmbeddings()
 
 
-
-
 # Step4. Load the vector store
-from langchain.vectorstores import Epsilla
+from langchain_community.vectorstores import Epsilla
 from pyepsilla import vectordb
 
 db_client = vectordb.Client(protocol="https", host="demo.epsilla.com", port="443")
@@ -56,11 +49,12 @@
 )
 
 
+
+
 # Step4. Create the QA for Retrieval
 from langchain.chains import RetrievalQA
 from langchain_openai import OpenAI
 
-
 qa = RetrievalQA.from_chain_type(
     llm=OpenAI(), chain_type="stuff", retriever=vector_store.as_retriever()
 )

examples/Question_Answering_Pipeline_with_LangChain_and_EpsillaCloud.py

@@ -10,43 +10,35 @@
 pip install tiktoken
 pip install pyepsilla
 pip install -U langchain-openai
-pip uninstall -y langchain-community
-git clone https://github.com/epsilla-cloud/langchain.git
-cd ./langchain/libs/community
-pip install .
+pip install -U langchain-community
 """
 
 
-
 # Step2. Configure the OpenAI API Key
 import os
 
-os.environ["OPENAI_API_KEY"] = ""
-epsilla_api_key = os.getenv("EPSILLA_API_KEY", "")
-project_id = os.getenv("EPSILLA_PROJECT_ID", "")
-db_id = os.getenv("EPSILLA_DB_ID", "")
+os.environ["OPENAI_API_KEY"] = "Your-OpenAI-API-Key"
+epsilla_api_key = os.getenv("EPSILLA_API_KEY", "Your-Epsilla-API-Key")
+project_id = os.getenv("EPSILLA_PROJECT_ID", "Your-Project-ID")
+db_id = os.getenv("EPSILLA_DB_ID", "Your-DB-ID")
 db_sharding_id = os.getenv("EPSILLA_DB_SHARDING_ID", 0)
 
+
 # Step3. Load the documents
 from langchain.document_loaders import WebBaseLoader
 from langchain.text_splitter import CharacterTextSplitter
 from langchain_openai import OpenAIEmbeddings
 
-loader = WebBaseLoader(
-    "https://raw.githubusercontent.com/hwchase17/chat-your-data/master/state_of_the_union.txt"
-)
+loader = WebBaseLoader("https://raw.githubusercontent.com/hwchase17/chat-your-data/master/state_of_the_union.txt")
 documents = loader.load()
-documents = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0).split_documents(
-    documents
-)
+documents = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0).split_documents(documents)
 embeddings = OpenAIEmbeddings()
 
 
 # Step4. Load the vector store
-from langchain.vectorstores import Epsilla
+from langchain_community.vectorstores import Epsilla
 from pyepsilla import cloud, vectordb
 
-
 db_name = f"db_{db_id.replace('-', '_')}"
 db_path = f"/data/{project_id}/{db_name}/s{db_sharding_id}"
 table_name = "MyCollection"
@@ -69,6 +61,8 @@
     collection_name=table_name,
 )
 
+
+
 # Step4. Create the QA for Retrieval
 from langchain.chains import RetrievalQA
 from langchain_openai import OpenAI