mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-29 07:19:59 +00:00
72bfc1d3db
This PR migrates the existing MongoDBAtlasVectorSearch abstraction from
the `langchain_community` section to the partners package section of the
codebase.
- [x] Run the partner package script as advised in the partner-packages
documentation.
- [x] Add Unit Tests
- [x] Migrate Integration Tests
- [x] Refactor `MongoDBAtlasVectorStore` (autogenerated) to
`MongoDBAtlasVectorSearch`
- [x] ~Remove~ deprecate the old `langchain_community` VectorStore
references.
## Additional Callouts
- Implemented the `delete` method
- Included any missing async function implementations
- `amax_marginal_relevance_search_by_vector`
- `adelete`
- Added new Unit Tests that test for functionality of
`MongoDBVectorSearch` methods
- Removed [`del
res[self._embedding_key]`](e0c81e1cb0/libs/community/langchain_community/vectorstores/mongodb_atlas.py (L218))
in `_similarity_search_with_score` function as it would make the
`maximal_marginal_relevance` function fail otherwise. The `Document`
needs to store the embedding key in metadata to work.
Checklist:
- [x] PR title: Please title your PR "package: description", where
"package" is whichever of langchain, community, core, experimental, etc.
is being modified. Use "docs: ..." for purely docs changes, "templates:
..." for template changes, "infra: ..." for CI changes.
- Example: "community: add foobar LLM"
- [x] PR message
- [x] Pass lint and test: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified to check that you're
passing lint and testing. See contribution guidelines for more
information on how to write/run tests, lint, etc:
https://python.langchain.com/docs/contributing/
- [x] Add tests and docs: If you're adding a new integration, please
include
1. Existing tests supplied in docs/docs do not change. Updated
docstrings for new functions like `delete`
2. an example notebook showing its use. It lives in
`docs/docs/integrations` directory. (This already exists)
If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.
---------
Co-authored-by: Steven Silvester <steven.silvester@ieee.org>
Co-authored-by: Erick Friis <erick@langchain.dev>
37 lines
1.3 KiB
Python
37 lines
1.3 KiB
Python
from __future__ import annotations
|
|
|
|
from typing import List
|
|
|
|
from langchain_core.embeddings import Embeddings
|
|
|
|
|
|
class ConsistentFakeEmbeddings(Embeddings):
|
|
"""Fake embeddings functionality for testing."""
|
|
|
|
def __init__(self, dimensionality: int = 10) -> None:
|
|
self.known_texts: List[str] = []
|
|
self.dimensionality = dimensionality
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""Return consistent embeddings for each text seen so far."""
|
|
out_vectors = []
|
|
for text in texts:
|
|
if text not in self.known_texts:
|
|
self.known_texts.append(text)
|
|
vector = [float(1.0)] * (self.dimensionality - 1) + [
|
|
float(self.known_texts.index(text))
|
|
]
|
|
out_vectors.append(vector)
|
|
return out_vectors
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""Return consistent embeddings for the text, if seen before, or a constant
|
|
one if the text is unknown."""
|
|
return self.embed_documents([text])[0]
|
|
|
|
async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
return self.embed_documents(texts)
|
|
|
|
async def aembed_query(self, text: str) -> List[float]:
|
|
return self.embed_query(text)
|