qdrant[patch]: Use collection_exists API instead of exceptions (#22764)

## Description

Currently, the Qdrant integration relies on exceptions raised by
[`get_collection`
](https://qdrant.tech/documentation/concepts/collections/#collection-info)
to check if a collection exists.

Using
[`collection_exists`](https://qdrant.tech/documentation/concepts/collections/#check-collection-existence)
is recommended to avoid missing any unhandled exceptions. This PR
addresses this.

## Testing
All integration and unit tests pass. No user-facing changes.
This commit is contained in:
Anush
2024-06-14 08:31:32 +05:30
committed by GitHub
parent c417803908
commit e002c855bd
3 changed files with 25 additions and 27 deletions

View File

@@ -23,14 +23,12 @@ from typing import (
)
import numpy as np
from grpc import RpcError # type: ignore
from langchain_core.documents import Document
from langchain_core.embeddings import Embeddings
from langchain_core.runnables.config import run_in_executor
from langchain_core.vectorstores import VectorStore
from qdrant_client import AsyncQdrantClient, QdrantClient
from qdrant_client.http import models
from qdrant_client.http.exceptions import UnexpectedResponse
from qdrant_client.local.async_qdrant_local import AsyncQdrantLocal
from langchain_qdrant._utils import maximal_marginal_relevance
@@ -1636,14 +1634,16 @@ class Qdrant(VectorStore):
path=path,
**kwargs,
)
try:
# Skip any validation in case of forced collection recreate.
if force_recreate:
raise ValueError
collection_exists = client.collection_exists(collection_name)
if collection_exists and force_recreate:
client.delete_collection(collection_name)
collection_exists = False
if collection_exists:
# Get the vector configuration of the existing collection and vector, if it
# was specified. If the old configuration does not match the current one,
# an exception is being thrown.
# an exception is raised.
collection_info = client.get_collection(collection_name=collection_name)
current_vector_config = collection_info.config.params.vectors
if isinstance(current_vector_config, dict) and vector_name is not None:
@@ -1700,7 +1700,7 @@ class Qdrant(VectorStore):
f"If you want to recreate the collection, set `force_recreate` "
f"parameter to `True`."
)
except (UnexpectedResponse, RpcError, ValueError):
else:
vectors_config = models.VectorParams(
size=vector_size,
distance=models.Distance[distance_func],
@@ -1714,8 +1714,6 @@ class Qdrant(VectorStore):
vector_name: vectors_config,
}
if client.collection_exists(collection_name):
client.delete_collection(collection_name)
client.create_collection(
collection_name=collection_name,
vectors_config=vectors_config,
@@ -1795,14 +1793,17 @@ class Qdrant(VectorStore):
path=path,
**kwargs,
)
try:
# Skip any validation in case of forced collection recreate.
if force_recreate:
raise ValueError
collection_exists = client.collection_exists(collection_name)
if collection_exists and force_recreate:
client.delete_collection(collection_name)
collection_exists = False
if collection_exists:
# Get the vector configuration of the existing collection and vector, if it
# was specified. If the old configuration does not match the current one,
# an exception is being thrown.
# an exception is raised.
collection_info = client.get_collection(collection_name=collection_name)
current_vector_config = collection_info.config.params.vectors
if isinstance(current_vector_config, dict) and vector_name is not None:
@@ -1861,7 +1862,7 @@ class Qdrant(VectorStore):
f"recreate the collection, set `force_recreate` parameter to "
f"`True`."
)
except (UnexpectedResponse, RpcError, ValueError):
else:
vectors_config = models.VectorParams(
size=vector_size,
distance=models.Distance[distance_func],
@@ -1875,7 +1876,7 @@ class Qdrant(VectorStore):
vector_name: vectors_config,
}
client.recreate_collection(
client.create_collection(
collection_name=collection_name,
vectors_config=vectors_config,
shard_number=shard_number,