f8cf09a230
This PR updates the Vectara integration (@hwchase17 ): * Adds reuse of requests.session to imrpove efficiency and speed. * Utilizes Vectara's low-level API (instead of standard API) to better match user's specific chunking with LangChain * Now add_texts puts all the texts into a single Vectara document so indexing is much faster. * updated variables names from alpha to lambda_val (to be consistent with Vectara docs) and added n_context_sentence so it's available to use if needed. * Updates to documentation and tests --------- Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
3.0 KiB
Vectara
What is Vectara?
Vectara Overview:
- Vectara is developer-first API platform for building GenAI applications
- To use Vectara - first sign up and create an account. Then create a corpus and an API key for indexing and searching.
- You can use Vectara's indexing API to add documents into Vectara's index
- You can use Vectara's Search API to query Vectara's index (which also supports Hybrid search implicitly).
- You can use Vectara's integration with LangChain as a Vector store or using the Retriever abstraction.
Installation and Setup
To use Vectara with LangChain no special installation steps are required. You just have to provide your customer_id, corpus ID, and an API key created within the Vectara console to enable indexing and searching.
Alternatively these can be provided as environment variables
- export
VECTARA_CUSTOMER_ID="your_customer_id" - export
VECTARA_CORPUS_ID="your_corpus_id" - export
VECTARA_API_KEY="your-vectara-api-key"
Usage
VectorStore
There exists a wrapper around the Vectara platform, allowing you to use it as a vectorstore, whether for semantic search or example selection.
To import this vectorstore:
from langchain.vectorstores import Vectara
To create an instance of the Vectara vectorstore:
vectara = Vectara(
vectara_customer_id=customer_id,
vectara_corpus_id=corpus_id,
vectara_api_key=api_key
)
The customer_id, corpus_id and api_key are optional, and if they are not supplied will be read from the environment variables VECTARA_CUSTOMER_ID, VECTARA_CORPUS_ID and VECTARA_API_KEY, respectively.
To query the vectorstore, you can use the similarity_search method (or similarity_search_with_score), which takes a query string and returns a list of results:
results = vectara.similarity_score("what is LangChain?")
similarity_search_with_score also supports the following additional arguments:
k: number of results to return (defaults to 5)lambda_val: the lexical matching factor for hybrid search (defaults to 0.025)filter: a filter 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 0 so as to return the exact text segment that matches, but can be used with other values e.g. 2 or 3 to return adjacent text segments.
The results are returned as a list of relevant documents, and a relevance score of each document.
For a more detailed examples of using the Vectara wrapper, see one of these two sample notebooks: