langchain/templates/rag-vectara-multiquery/rag_vectara_multiquery/chain.py
Bagatur 480626dc99
docs, community[patch], experimental[patch], langchain[patch], cli[pa… (#15412)
…tch]: import models from community

ran
```bash
git grep -l 'from langchain\.chat_models' | xargs -L 1 sed -i '' "s/from\ langchain\.chat_models/from\ langchain_community.chat_models/g"
git grep -l 'from langchain\.llms' | xargs -L 1 sed -i '' "s/from\ langchain\.llms/from\ langchain_community.llms/g"
git grep -l 'from langchain\.embeddings' | xargs -L 1 sed -i '' "s/from\ langchain\.embeddings/from\ langchain_community.embeddings/g"
git checkout master libs/langchain/tests/unit_tests/llms
git checkout master libs/langchain/tests/unit_tests/chat_models
git checkout master libs/langchain/tests/unit_tests/embeddings/test_imports.py
make format
cd libs/langchain; make format
cd ../experimental; make format
cd ../core; make format
```
2024-01-02 15:32:16 -05:00

58 lines
2.3 KiB
Python

import os
from langchain.retrievers.multi_query import MultiQueryRetriever
from langchain.vectorstores import Vectara
from langchain_community.chat_models import ChatOpenAI
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]]
model = ChatOpenAI()
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)