Hippo

%pip install --upgrade --quiet  langchain langchain_community tiktoken langchain-openai
%pip install --upgrade --quiet  hippo-api==1.1.0.rc3

import os

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores.hippo import Hippo
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_text_splitters import CharacterTextSplitter

os.environ["OPENAI_API_KEY"] = "YOUR OPENAI KEY"
loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()

text_splitter = CharacterTextSplitter(chunk_size=500, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

# openai
embeddings = OpenAIEmbeddings()
# azure
# embeddings = OpenAIEmbeddings(
#     openai_api_type="azure",
#     openai_api_base="x x x",
#     openai_api_version="x x x",
#     model="x x x",
#     deployment="x x x",
#     openai_api_key="x x x"
# )

HIPPO_CONNECTION = {"host": "IP", "port": "PORT"}

print("input...")
# insert docs
vector_store = Hippo.from_documents(
    docs,
    embedding=embeddings,
    table_name="langchain_test",
    connection_args=HIPPO_CONNECTION,
)
print("success")

# llm = AzureChatOpenAI(
#     openai_api_base="x x x",
#     openai_api_version="xxx",
#     deployment_name="xxx",
#     openai_api_key="xxx",
#     openai_api_type="azure"
# )

llm = ChatOpenAI(openai_api_key="YOUR OPENAI KEY", model_name="gpt-3.5-turbo-16k")

query = "Please introduce COVID-19"
# query = "Please introduce Hippo Core Architecture"
# query = "What operations does the Hippo Vector Database support for vector data?"
# query = "Does Hippo use hardware acceleration technology? Briefly introduce hardware acceleration technology."


# Retrieve similar content from the knowledge base,fetch the top two most similar texts.
res = vector_store.similarity_search(query, 2)
content_list = [item.page_content for item in res]
text = "".join(content_list)

prompt = f"""
Please use the content of the following [Article] to answer my question. If you don't know, please say you don't know, and the answer should be concise."
[Article]:{text}
Please answer this question in conjunction with the above article:{query}
"""

response_with_hippo = llm.predict(prompt)
print(f"response_with_hippo:{response_with_hippo}")
response = llm.predict(query)
print("==========================================")
print(f"response_without_hippo:{response}")