langchain/templates/rag-timescale-hybrid-search-time/rag_timescale_hybrid_search_time/chain.py
Lance Martin da94c750c5
Add RAG template for Timescale Vector (#12651)
<!-- Thank you for contributing to LangChain!

Replace this entire comment with:
  - **Description:** a description of the change, 
  - **Issue:** the issue # it fixes (if applicable),
  - **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in `docs/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

---------

Co-authored-by: Matvey Arye <mat@timescale.com>
2023-10-31 09:56:29 -07:00

113 lines
3.2 KiB
Python

# ruff: noqa: E501
import os
from datetime import timedelta
from langchain.chains.query_constructor.base import AttributeInfo
from langchain.chat_models import ChatOpenAI
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.llms import OpenAI
from langchain.prompts import ChatPromptTemplate
from langchain.retrievers.self_query.base import SelfQueryRetriever
from langchain.schema.output_parser import StrOutputParser
from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
from langchain.vectorstores.timescalevector import TimescaleVector
from pydantic import BaseModel
from .load_sample_dataset import load_ts_git_dataset
# to enable debug uncomment the following lines:
# from langchain.globals import set_debug
# set_debug(True)
# from dotenv import find_dotenv, load_dotenv
# _ = load_dotenv(find_dotenv())
if os.environ.get("TIMESCALE_SERVICE_URL", None) is None:
raise Exception("Missing `TIMESCALE_SERVICE_URL` environment variable.")
SERVICE_URL = os.environ["TIMESCALE_SERVICE_URL"]
LOAD_SAMPLE_DATA = os.environ.get("LOAD_SAMPLE_DATA", False)
# DATASET SPECIFIC CODE
# Load the sample dataset. You will have to change this to load your own dataset.
collection_name = "timescale_commits"
partition_interval = timedelta(days=7)
if LOAD_SAMPLE_DATA:
load_ts_git_dataset(
SERVICE_URL,
collection_name=collection_name,
num_records=500,
partition_interval=partition_interval,
)
# This will change depending on the metadata stored in your dataset.
document_content_description = "The git log commit summary containing the commit hash, author, date of commit, change summary and change details"
metadata_field_info = [
AttributeInfo(
name="id",
description="A UUID v1 generated from the date of the commit",
type="uuid",
),
AttributeInfo(
# This is a special attribute represent the timestamp of the uuid.
name="__uuid_timestamp",
description="The timestamp of the commit. Specify in YYYY-MM-DDTHH::MM:SSZ format",
type="datetime.datetime",
),
AttributeInfo(
name="author_name",
description="The name of the author of the commit",
type="string",
),
AttributeInfo(
name="author_email",
description="The email address of the author of the commit",
type="string",
),
]
# END DATASET SPECIFIC CODE
embeddings = OpenAIEmbeddings()
vectorstore = TimescaleVector(
embedding=embeddings,
collection_name=collection_name,
service_url=SERVICE_URL,
time_partition_interval=partition_interval,
)
llm = OpenAI(temperature=0)
retriever = SelfQueryRetriever.from_llm(
llm,
vectorstore,
document_content_description,
metadata_field_info,
enable_limit=True,
verbose=True,
)
template = """Answer the question based only on the following context:
{context}
Question: {question}
"""
prompt = ChatPromptTemplate.from_template(template)
model = ChatOpenAI(temperature=0, model="gpt-4")
# RAG chain
chain = (
RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
| prompt
| model
| StrOutputParser()
)
class Question(BaseModel):
__root__: str
chain = chain.with_types(input_type=Question)