2023-11-10 18:08:45 +00:00
|
|
|
import os
|
|
|
|
|
|
|
|
|
|
from langchain.retrievers.multi_query import MultiQueryRetriever
|
2024-01-02 20:32:16 +00:00
|
|
|
from langchain_community.chat_models import ChatOpenAI
|
2024-01-02 21:47:11 +00:00
|
|
|
from langchain_community.vectorstores import Vectara
|
docs[patch], templates[patch]: Import from core (#14575)
Update imports to use core for the low-hanging fruit changes. Ran
following
```bash
git grep -l 'langchain.schema.runnable' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.runnable/langchain_core.runnables/g'
git grep -l 'langchain.schema.output_parser' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.output_parser/langchain_core.output_parsers/g'
git grep -l 'langchain.schema.messages' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.messages/langchain_core.messages/g'
git grep -l 'langchain.schema.chat_histry' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.chat_history/langchain_core.chat_history/g'
git grep -l 'langchain.schema.prompt_template' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.prompt_template/langchain_core.prompts/g'
git grep -l 'from langchain.pydantic_v1' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.pydantic_v1/from langchain_core.pydantic_v1/g'
git grep -l 'from langchain.tools.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.tools\.base/from langchain_core.tools/g'
git grep -l 'from langchain.chat_models.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.chat_models.base/from langchain_core.language_models.chat_models/g'
git grep -l 'from langchain.llms.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.llms\.base\ /from langchain_core.language_models.llms\ /g'
git grep -l 'from langchain.embeddings.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.embeddings\.base/from langchain_core.embeddings/g'
git grep -l 'from langchain.vectorstores.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.vectorstores\.base/from langchain_core.vectorstores/g'
git grep -l 'from langchain.agents.tools' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.agents\.tools/from langchain_core.tools/g'
git grep -l 'from langchain.schema.output' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.output\ /from langchain_core.outputs\ /g'
git grep -l 'from langchain.schema.embeddings' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.embeddings/from langchain_core.embeddings/g'
git grep -l 'from langchain.schema.document' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.document/from langchain_core.documents/g'
git grep -l 'from langchain.schema.agent' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.agent/from langchain_core.agents/g'
git grep -l 'from langchain.schema.prompt ' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.prompt\ /from langchain_core.prompt_values /g'
git grep -l 'from langchain.schema.language_model' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.language_model/from langchain_core.language_models/g'
```
2023-12-12 00:49:10 +00:00
|
|
|
from langchain_core.output_parsers import StrOutputParser
|
|
|
|
|
from langchain_core.pydantic_v1 import BaseModel
|
|
|
|
|
from langchain_core.runnables import RunnableParallel, RunnablePassthrough
|
2023-11-10 18:08:45 +00:00
|
|
|
|
|
|
|
|
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.")
|
|
|
|
|
|
|
|
|
|
|
2023-12-20 19:51:33 +00:00
|
|
|
# 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
|
2023-11-10 18:08:45 +00:00
|
|
|
llm = ChatOpenAI(temperature=0)
|
2023-12-20 19:51:33 +00:00
|
|
|
retriever = MultiQueryRetriever.from_llm(retriever=vectara_retriever, llm=llm)
|
2023-11-10 18:08:45 +00:00
|
|
|
|
2023-12-20 19:51:33 +00:00
|
|
|
# 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]]
|
2023-11-10 18:08:45 +00:00
|
|
|
chain = (
|
|
|
|
|
RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
|
2023-12-20 19:51:33 +00:00
|
|
|
| (lambda res: res[-1])
|
2023-11-10 18:08:45 +00:00
|
|
|
| StrOutputParser()
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# Add typing for input
|
|
|
|
|
class Question(BaseModel):
|
|
|
|
|
__root__: str
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
chain = chain.with_types(input_type=Question)
|
