mirror of
https://github.com/hwchase17/langchain
synced 2024-10-29 17:07:25 +00:00
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>
37 lines
1.4 KiB
Python
37 lines
1.4 KiB
Python
from langchain.docstore.document import Document
|
|
from langchain.vectorstores.vectara import Vectara
|
|
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
|
|
|
|
|
|
def get_abbr(s: str) -> str:
|
|
words = s.split(" ") # Split the string into words
|
|
first_letters = [word[0] for word in words] # Extract the first letter of each word
|
|
return "".join(first_letters) # Join the first letters into a single string
|
|
|
|
|
|
def test_vectara_add_documents() -> None:
|
|
"""Test end to end construction and search."""
|
|
|
|
# start with some initial documents
|
|
texts = ["grounded generation", "retrieval augmented generation", "data privacy"]
|
|
docsearch: Vectara = Vectara.from_texts(
|
|
texts,
|
|
embedding=FakeEmbeddings(),
|
|
metadatas=[{"abbr": "gg"}, {"abbr": "rag"}, {"abbr": "dp"}],
|
|
)
|
|
|
|
# then add some additional documents
|
|
new_texts = ["large language model", "information retrieval", "question answering"]
|
|
docsearch.add_documents(
|
|
[Document(page_content=t, metadata={"abbr": get_abbr(t)}) for t in new_texts]
|
|
)
|
|
|
|
# finally do a similarity search to see if all works okay
|
|
output = docsearch.similarity_search(
|
|
"large language model", k=2, n_sentence_context=0
|
|
)
|
|
assert output[0].page_content == "large language model"
|
|
assert output[0].metadata == {"abbr": "llm"}
|
|
assert output[1].page_content == "information retrieval"
|
|
assert output[1].metadata == {"abbr": "ir"}
|