mirror of
https://github.com/hwchase17/langchain.git
synced 2026-04-03 19:04:23 +00:00
edd68e4ad4
## Description This PR introduces the new `langchain-qdrant` partner package, intending to deprecate the community package. ## Changes - Moved the Qdrant vector store implementation `/libs/partners/qdrant` with integration tests. - The conditional imports of the client library are now regular with minor implementation improvements. - Added a deprecation warning to `langchain_community.vectorstores.qdrant.Qdrant`. - Replaced references/imports from `langchain_community` with either `langchain_core` or by moving the definitions to the `langchain_qdrant` package itself. - Updated the Qdrant vector store documentation to reflect the changes. ## Testing - `QDRANT_URL` and [`QDRANT_API_KEY`](583e36bf6b) env values need to be set to [run integration tests](d608c93d1f) in the [cloud](https://cloud.qdrant.tech). - If a Qdrant instance is running at `http://localhost:6333`, the integration tests will use it too. - By default, tests use an [`in-memory`](https://github.com/qdrant/qdrant-client?tab=readme-ov-file#local-mode) instance(Not comprehensive). --------- Co-authored-by: Erick Friis <erick@langchain.dev> Co-authored-by: Erick Friis <erickfriis@gmail.com>
80 lines
2.9 KiB
Python
80 lines
2.9 KiB
Python
from typing import List
|
|
|
|
import requests # type: ignore
|
|
from langchain_core.documents import Document
|
|
from langchain_core.embeddings import Embeddings
|
|
|
|
|
|
def qdrant_running_locally() -> bool:
|
|
"""Check if Qdrant is running at http://localhost:6333."""
|
|
|
|
try:
|
|
response = requests.get("http://localhost:6333", timeout=10.0)
|
|
response_json = response.json()
|
|
return response_json.get("title") == "qdrant - vector search engine"
|
|
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout):
|
|
return False
|
|
|
|
|
|
def assert_documents_equals(actual: List[Document], expected: List[Document]): # type: ignore[no-untyped-def]
|
|
assert len(actual) == len(expected)
|
|
|
|
for actual_doc, expected_doc in zip(actual, expected):
|
|
assert actual_doc.page_content == expected_doc.page_content
|
|
|
|
assert "_id" in actual_doc.metadata
|
|
assert "_collection_name" in actual_doc.metadata
|
|
|
|
actual_doc.metadata.pop("_id")
|
|
actual_doc.metadata.pop("_collection_name")
|
|
|
|
assert actual_doc.metadata == expected_doc.metadata
|
|
|
|
|
|
class FakeEmbeddings(Embeddings):
|
|
"""Fake embeddings functionality for testing."""
|
|
|
|
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
"""Return simple embeddings.
|
|
Embeddings encode each text as its index."""
|
|
return [[float(1.0)] * 9 + [float(i)] for i in range(len(texts))]
|
|
|
|
async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
|
|
return self.embed_documents(texts)
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
"""Return constant query embeddings.
|
|
Embeddings are identical to embed_documents(texts)[0].
|
|
Distance to each text will be that text's index,
|
|
as it was passed to embed_documents."""
|
|
return [float(1.0)] * 9 + [float(0.0)]
|
|
|
|
async def aembed_query(self, text: str) -> List[float]:
|
|
return self.embed_query(text)
|
|
|
|
|
|
class ConsistentFakeEmbeddings(FakeEmbeddings):
|
|
"""Fake embeddings which remember all the texts seen so far to return consistent
|
|
vectors for the same texts."""
|
|
|
|
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]
|