Qdrant client causes Pydantic validation error if QDRANT__SERVICE__HARDWARE_REPORTING=true is passed

[shahad-mahmud]

I'm running Qdrant locally with docker using docker compose. When I pass QDRANT__SERVICE__HARDWARE_REPORTING=true and try to use it with python client, it causes Pydantic validation error.

Current Behavior

It raises the following exception:

Traceback (most recent call last):
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/qdrant_client/http/api_client.py", line 109, in send
    return parse_as_type(response.json(), type_)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/qdrant_client/http/api_client.py", line 228, in parse_as_type
    return model_type(obj=obj).obj
           ^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/pydantic/main.py", line 214, in __init__
    validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
pydantic_core._pydantic_core.ValidationError: 2 validation errors for ParsingModel[InlineResponse2006] (for parse_as_type)
obj.usage.io_read
  Field required [type=missing, input_value={'cpu': 0, 'payload_io_re...vector_io_write': 16384}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing
obj.usage.io_write
  Field required [type=missing, input_value={'cpu': 0, 'payload_io_re...vector_io_write': 16384}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/shahad/Documents/codes/delineate/ai-infra/qdrant-db/minimal.py", line 43, in <module>
    vector_store.add_documents(users)
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/langchain_core/vectorstores/base.py", line 286, in add_documents
    return self.add_texts(texts, metadatas, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/langchain_qdrant/qdrant.py", line 444, in add_texts
    self.client.upsert(
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/qdrant_client/qdrant_client.py", line 1567, in upsert
    return self._client.upsert(
           ^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/qdrant_client/qdrant_remote.py", line 1908, in upsert
    http_result = self.openapi_client.points_api.upsert_points(
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/qdrant_client/http/api/points_api.py", line 987, in upsert_points
    return self._build_for_upsert_points(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/qdrant_client/http/api/points_api.py", line 512, in _build_for_upsert_points
    return self.api_client.request(
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/qdrant_client/http/api_client.py", line 89, in request
    return self.send(request, type_)
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/miniconda3/envs/delineate/lib/python3.11/site-packages/qdrant_client/http/api_client.py", line 111, in send
    raise ResponseHandlingException(e)
qdrant_client.http.exceptions.ResponseHandlingException: 2 validation errors for ParsingModel[InlineResponse2006] (for parse_as_type)
obj.usage.io_read
  Field required [type=missing, input_value={'cpu': 0, 'payload_io_re...vector_io_write': 16384}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing
obj.usage.io_write
  Field required [type=missing, input_value={'cpu': 0, 'payload_io_re...vector_io_write': 16384}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing

Steps to Reproduce

1. Use the following docker compose:

services:
  qdrant:
    image: qdrant/qdrant:v1.13.5
    restart: always
    container_name: qdrant
    ports:
      - 7233:6333
      - 7234:6334
    expose:
      - 6333
      - 6334
      - 6335
    volumes:
      - ./data/qdrant_data:/qdrant/storage
    environment:
      - QDRANT__SERVICE__API_KEY=123456
      - QDRANT__SERVICE__JWT_RBAC=true
      - QDRANT__SERVICE__HARDWARE_REPORTING=true

configs:
  qdrant_config:
    content: |
      log_level: INFO

Then you can use the following code:

from qdrant_client import QdrantClient
from qdrant_client.models import VectorParams, Distance
import json

from langchain_qdrant import QdrantVectorStore
from langchain_openai import OpenAIEmbeddings
from langchain_core.documents import Document

from dotenv import load_dotenv

load_dotenv()


client = QdrantClient(url="http://localhost:7233", api_key="123456", https=True)

if not client.collection_exists("users"):
    client.create_collection(
        "users", vectors_config=VectorParams(size=2048, distance=Distance.COSINE)
    )

vector_store = QdrantVectorStore(
    client=client,
    collection_name="users",
    embedding=OpenAIEmbeddings(
        model="text-embedding-3-large",
        dimensions=2048,
        disallowed_special=(),
    ),
)

users = [
    Document(
        page_content="admin",
        metadata={"user": "admin", "role": "admin", "revoked": False},
    ),
    Document(
        page_content="canary",
        metadata={"user": "canary", "role": "admin", "revoked": False},
    ),
]


vector_store.add_documents(users)

Expected Behavior

The client should not get any issue after some points are pushed.

Context (Environment)

using the following qdrant related packages:

langchain-qdrant==0.2.0
qdrant-client==1.13.3

docker tag: qdrant/qdrant:v1.13.5

[joein]

hey @shahad-mahmud

This feature is not stable yet, I'd recommend to disable it

Once it is supported in qdrant, qdrant-client won't throw exceptions, but access to these metrics in qdrant-client has not been planned yet