mirror of
https://github.com/hwchase17/langchain
synced 2024-11-02 09:40:22 +00:00
ffae98d371
fixed multi-query template for Vectara added self-query template for Vectara Also added prompt_name parameter to summarization CC @efriis **Twitter handle:** @ofermend
57 lines
2.3 KiB
Python
57 lines
2.3 KiB
Python
import os
|
|
|
|
from langchain.retrievers.multi_query import MultiQueryRetriever
|
|
from langchain_community.chat_models import ChatOpenAI
|
|
from langchain_community.vectorstores import Vectara
|
|
from langchain_core.output_parsers import StrOutputParser
|
|
from langchain_core.pydantic_v1 import BaseModel
|
|
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
|
|
|
|
if os.environ.get("VECTARA_CUSTOMER_ID", None) is None:
|
|
raise Exception("Missing `VECTARA_CUSTOMER_ID` environment variable.")
|
|
if os.environ.get("VECTARA_CORPUS_ID", None) is None:
|
|
raise Exception("Missing `VECTARA_CORPUS_ID` environment variable.")
|
|
if os.environ.get("VECTARA_API_KEY", None) is None:
|
|
raise Exception("Missing `VECTARA_API_KEY` environment variable.")
|
|
|
|
|
|
# Setup the Vectara retriever with your Corpus ID and API Key
|
|
|
|
# note you can customize the retriever behavior by passing additional arguments:
|
|
# - k: number of results to return (defaults to 5)
|
|
# - lambda_val: the
|
|
# [lexical matching](https://docs.vectara.com/docs/api-reference/search-apis/lexical-matching)
|
|
# factor for hybrid search (defaults to 0.025)
|
|
# - filter: a [filter](https://docs.vectara.com/docs/common-use-cases/filtering-by-metadata/filter-overview)
|
|
# to apply to the results (default None)
|
|
# - n_sentence_context: number of sentences to include before/after the actual matching
|
|
# segment when returning results. This defaults to 2.
|
|
# - mmr_config: can be used to specify MMR mode in the query.
|
|
# - is_enabled: True or False
|
|
# - mmr_k: number of results to use for MMR reranking
|
|
# - diversity_bias: 0 = no diversity, 1 = full diversity. This is the lambda
|
|
# parameter in the MMR formula and is in the range 0...1
|
|
vectara_retriever = Vectara().as_retriever()
|
|
|
|
# Setup the Multi-query retriever
|
|
llm = ChatOpenAI(temperature=0)
|
|
retriever = MultiQueryRetriever.from_llm(retriever=vectara_retriever, llm=llm)
|
|
|
|
# Setup RAG pipeline with multi-query.
|
|
# We extract the summary from the RAG output, which is the last document
|
|
# (if summary is enabled)
|
|
# Note that if you want to extract the citation information, you can use res[:-1]]
|
|
chain = (
|
|
RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
|
|
| (lambda res: res[-1])
|
|
| StrOutputParser()
|
|
)
|
|
|
|
|
|
# Add typing for input
|
|
class Question(BaseModel):
|
|
__root__: str
|
|
|
|
|
|
chain = chain.with_types(input_type=Question)
|