Ragie integration for LangChain
Project description
langchain-ragie
Ragie (https://ragie.ai) integration for LangChain
Install
pip install langchain-ragie
Usage
If you need asyncio, see this example..
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
import langchain_ragie
template = """Answer the question based only on the following context:
{context}
Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)
model = ChatOpenAI()
retriever = langchain_ragie.RagieRetriever()
def format_docs(docs):
return "\n\n".join([d.page_content for d in docs])
chain = (
{"context": retriever | format_docs, "question": RunnablePassthrough()}
| prompt
| model
| StrOutputParser()
)
response = chain.invoke("What do the besties think about Davos?")
print(response)
License
Distributed under the MIT License. See LICENSE.txt
for more information.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
langchain_ragie-0.3.0.tar.gz
(3.3 kB
view hashes)
Built Distribution
Close
Hashes for langchain_ragie-0.3.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d7c6805d053f0f2f4ccffdf1b5b60d5ae569cf04f83db3b118a705383c391501 |
|
MD5 | fab21856481ec74460cd415b0db02d7d |
|
BLAKE2b-256 | e31e1587728c3ceceb6efc7a9853b799d3f825db8e18d4de483a2c2b14ff4603 |