community[minor]: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks (#21334)

Thank you for contributing to LangChain!

**Description:** update to the Vectara / Langchain integration to
integrate new Vectara capabilities:
- Full RAG implemented as a Runnable with as_rag()
- Vectara chat supported with as_chat()
- Both support streaming response
- Updated documentation and example notebook to reflect all the changes
- Updated Vectara templates

**Twitter handle:** ofermend

**Add tests and docs**: no new tests or docs, but updated both existing
tests and existing docs

templates/rag-vectara-multiquery/README.md

@@ -5,7 +5,7 @@ This template performs multiquery RAG with vectara.
 
 ## Environment Setup
 
-Set the `OPENAI_API_KEY` environment variable to access the OpenAI models.
+Set the `OPENAI_API_KEY` environment variable to access the OpenAI models for the multi-query processing.
 
 Also, ensure the following environment variables are set:
 * `VECTARA_CUSTOMER_ID`

templates/rag-vectara-multiquery/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "rag-vectara-multiquery"
-version = "0.1.0"
+version = "0.2.0"
 description = "RAG using vectara with multiquery retriever"
 authors = [
     "Ofer Mendelevitch <ofer@vectara.com>",

templates/rag-vectara-multiquery/rag_vectara_multiquery/chain.py

@@ -1,11 +1,12 @@
 import os
 
 from langchain.retrievers.multi_query import MultiQueryRetriever
-from langchain_community.chat_models import ChatOpenAI
 from langchain_community.vectorstores import Vectara
+from langchain_community.vectorstores.vectara import SummaryConfig, VectaraQueryConfig
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.pydantic_v1 import BaseModel
 from langchain_core.runnables import RunnableParallel, RunnablePassthrough
+from langchain_openai.chat_models import ChatOpenAI
 
 if os.environ.get("VECTARA_CUSTOMER_ID", None) is None:
     raise Exception("Missing `VECTARA_CUSTOMER_ID` environment variable.")
@@ -16,30 +17,20 @@ if os.environ.get("VECTARA_API_KEY", None) is None:
 
 
 # Setup the Vectara retriever with your Corpus ID and API Key
+vectara = Vectara()
 
-# 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()
+# Define the query configuration:
+summary_config = SummaryConfig(is_enabled=True, max_results=5, response_lang="eng")
+config = VectaraQueryConfig(k=10, lambda_val=0.005, summary_config=summary_config)
 
 # Setup the Multi-query retriever
 llm = ChatOpenAI(temperature=0)
-retriever = MultiQueryRetriever.from_llm(retriever=vectara_retriever, llm=llm)
+retriever = MultiQueryRetriever.from_llm(
+    retriever=vectara.as_retriever(config=config), 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)
+# We extract the summary from the RAG output, which is the last document in the list.
 # Note that if you want to extract the citation information, you can use res[:-1]]
 chain = (
     RunnableParallel({"context": retriever, "question": RunnablePassthrough()})

templates/rag-vectara/README.md

@@ -5,8 +5,6 @@ This template performs RAG with vectara.
 
 ## Environment Setup
 
-Set the `OPENAI_API_KEY` environment variable to access the OpenAI models.
-
 Also, ensure the following environment variables are set:
 * `VECTARA_CUSTOMER_ID`
 * `VECTARA_CORPUS_ID`

templates/rag-vectara/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "rag-vectara"
-version = "0.1.0"
+version = "0.2.0"
 description = "RAG using vectara retriever"
 authors = [
     "Ofer Mendelevitch <ofer@vectara.com>",

templates/rag-vectara/rag_vectara/chain.py

@@ -1,9 +1,8 @@
 import os
 
 from langchain_community.vectorstores import Vectara
-from langchain_core.output_parsers import StrOutputParser
+from langchain_community.vectorstores.vectara import SummaryConfig, VectaraQueryConfig
 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.")
@@ -12,32 +11,14 @@ if os.environ.get("VECTARA_CORPUS_ID", None) is None:
 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
+# Setup the Vectara vectorstore with your Corpus ID and API Key
+vectara = Vectara()
 
-# 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
-retriever = Vectara().as_retriever()
+# Define the query configuration:
+summary_config = SummaryConfig(is_enabled=True, max_results=5, response_lang="eng")
+config = VectaraQueryConfig(k=10, lambda_val=0.005, summary_config=summary_config)
 
-# RAG pipeline: 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()
-)
+rag = Vectara().as_rag(config)
 
 
 # Add typing for input
@@ -45,4 +26,4 @@ class Question(BaseModel):
     __root__: str
 
 
-chain = chain.with_types(input_type=Question)
+chain = rag.with_types(input_type=Question)