No project description provided
Project description
Dewy LangChain Plugin
This package provides Dewy integration for LangChain.
Example:
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from dewy_langchain import DewyRetriever
retriever = DewyRetriever.for_collection("main", base_url="http://localhost:8000")
prompt = ChatPromptTemplate.from_messages(
[
(
"system",
"""
You're a helpful AI assistant. Given a user question and some retrieved content, answer the user question.
If none of the articles answer the question, just say you don't know.
Here is the retrieved content:
{context}
""",
),
("human", "{question}"),
]
)
def format_chunks(chunks):
return "\n\n".join([d.page_content for d in chunks])
chain = (
{ "context": retriever | format_chunks, "question": RunnablePassthrough() }
| prompt
| llm
| StrOutputParser()
)
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
dewy_langchain-0.2.3.tar.gz
(2.0 kB
view hashes)
Built Distribution
Close
Hashes for dewy_langchain-0.2.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | e4bf95d7b50d95c26692e80d292523295daca4e41158ee813981acb31ee0c6c8 |
|
MD5 | 3e2716166ab485b24e80b0ab29991522 |
|
BLAKE2b-256 | e6cdc04d89c9916591cf050dc9449cbb3b16da55ae073a19f08052e5e44e34ba |