Fix read consistency when performing batch search

.github/workflows/integration-tests-macos.yml

@@ -13,11 +13,11 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - '3.7.x'
           - '3.8.x'
           - '3.9.x'
           - '3.10.x'
           - '3.11.x'
+          - '3.12.x'
         os:
           - macos-latest
 

.github/workflows/integration-tests.yml

@@ -18,6 +18,7 @@ jobs:
           - '3.9.x'
           - '3.10.x'
           - '3.11.x'
+          - '3.12.x'
         os:
           - ubuntu-latest
 
@@ -35,19 +36,32 @@ jobs:
         run: |
           python -m pip install poetry
           poetry config virtualenvs.create false
-          poetry install --no-interaction --no-ansi
+          poetry install --no-interaction --no-ansi --all-extras
+      - name: Run async client generation tests
+        run: |
+          if [[ ${{ matrix.python-version }} == "3.10.x" ]]; then
+            ./tests/async-client-consistency-check.sh
+          fi
+        shell: bash
+      - name: Run Python doc tests
+        run: |
+          python -m doctest qdrant_client/local/local_collection.py
       - name: Run integration tests
         run: |
           ./tests/integration-tests.sh
         shell: bash
       - name: Backward compatibility integration tests
         run: |
           export RUNNER_OS=${{ runner.os }}
-          QDRANT_VERSION='v1.3.2' ./tests/integration-tests.sh
+          QDRANT_VERSION='v1.7.4' ./tests/integration-tests.sh
+        shell: bash
+      - name: Run fastembed tests without fastembed
+        run: |
+          pip3 uninstall fastembed -y
+          pytest tests/test_fastembed.py
         shell: bash
       - name: Check conversion coverage
         run: |
           export RUNNER_OS=${{ runner.os }}
           ./tests/coverage-test.sh
         shell: bash
-

.github/workflows/type-checkers.yml

@@ -8,7 +8,7 @@ jobs:
     strategy:
       fail-fast: true
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
         os: [ubuntu-latest]
 
     name: Python ${{ matrix.python-version }} test
@@ -28,7 +28,10 @@ jobs:
 
       - name: mypy
         run: |
-          poetry run mypy . --disallow-incomplete-defs --disallow-untyped-defs
+          if [[ ${{ matrix.python-version }} != "3.8" ]] || [[ ! -d "tools/async_client_generator" ]]; then
+            # async_qdrant_fastembed.py is autogenerated and erases type ignore statements from the source code
+            poetry run mypy . --exclude "async_qdrant_fastembed.py" --disallow-incomplete-defs --disallow-untyped-defs
+          fi
 
       - name: pyright
         run: |

.gitignore

@@ -1,10 +1,16 @@
 venv
+.DS_Store
 __pycache__
 .pytest_cache
 .idea
+.vscode
+.devcontainer
 .coverage
 htmlcov
 *.iml
 dist
 *.tar.gz
 local_cache/*/*
+.python-version
+docs/source/examples/local_cache/*
+docs/source/examples/path/to/db/*

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
-#default_language_version:
-#   python: python3.8
+default_language_version:
+   python: python3.10
 
 exclude: 'qdrant_client/(grpc|http|models)/'
 
@@ -14,15 +14,15 @@ repos:
       - id: check-added-large-files
 
   - repo: https://github.com/psf/black
-    rev: 23.1.0
+    rev: 23.12.1
     hooks:
       - id: black
         name: "Black: The uncompromising Python code formatter"
         args: ["--line-length", "99"]
 
   - repo: https://github.com/PyCQA/isort
-    rev: 5.12.0
+    rev: 5.13.2
     hooks:
       - id: isort
         name: "Sort Imports"
-        args: ["--profile", "black"]
+        args: ["--profile", "black", "--py", "310"]

README.md

@@ -15,11 +15,12 @@
     <a href="https://github.com/qdrant/qdrant-client/blob/master/LICENSE"><img src="https://img.shields.io/badge/License-Apache%202.0-success" alt="Apache 2.0 License"></a>
     <a href="https://qdrant.to/discord"><img src="https://img.shields.io/badge/Discord-Qdrant-5865F2.svg?logo=discord" alt="Discord"></a>
     <a href="https://qdrant.to/roadmap"><img src="https://img.shields.io/badge/Roadmap-2023-bc1439.svg" alt="Roadmap 2023"></a>
+    <a href="https://python-client.qdrant.tech/"><img src="docs/images/api-icon.svg" width="30px"></a>
 </p>
 
 # Python Qdrant Client
 
-Client library and SDK for the [Qdrant](https://github.com/qdrant/qdrant) vector search engine.
+Client library and SDK for the [Qdrant](https://github.com/qdrant/qdrant) vector search engine. Python Client API Documentation is available [here](https://python-client.qdrant.tech/).
 
 Library contains type definitions for all Qdrant API and allows to make both Sync and Async requests.
 
@@ -70,7 +71,7 @@ Local mode is useful for development, prototyping and testing.
 ## Fast Embeddings + Simpler API
 
 ```
-pip install fastembed qdrant-client
+pip install qdrant-client[fastembed]
 ```
 
 FastEmbed is a library for creating fast vector embeddings on CPU. It is based on ONNX Runtime and allows to run inference on CPU with GPU-like performance.
@@ -85,16 +86,24 @@ client = QdrantClient(":memory:")  # or QdrantClient(path="path/to/db")
 
 # Prepare your documents, metadata, and IDs
 docs = ["Qdrant has Langchain integrations", "Qdrant also has Llama Index integrations"]
-metadatas = [
+metadata = [
     {"source": "Langchain-docs"},
     {"source": "Linkedin-docs"},
 ]
 ids = [42, 2]
 
 # Use the new add method
-client.add(collection_name="demo_collection", docs={"documents": docs, "metadatas": metadatas, "ids": ids})
+client.add(
+    collection_name="demo_collection",
+    documents=docs,
+    metadata=metadata,
+    ids=ids
+)
 
-search_result = client.query(collection_name="demo_collection", query_texts=["This is a query document"])
+search_result = client.query(
+    collection_name="demo_collection",
+    query_text="This is a query document"
+)
 print(search_result)
 ```
 
@@ -154,6 +163,9 @@ import numpy as np
 from qdrant_client.models import PointStruct
 
 vectors = np.random.rand(100, 100)
+# NOTE: consider splitting the data into chunks to avoid hitting the server's payload size limit
+# or use `upload_collection` or `upload_points` methods which handle this for you
+# WARNING: uploading points one-by-one is not recommended due to requests overhead
 client.upsert(
     collection_name="my_collection",
     points=[
@@ -215,23 +227,47 @@ client = QdrantClient(host="localhost", grpc_port=6334, prefer_grpc=True)
 
 ## Async client
 
-Async methods are available in raw autogenerated clients.
-Usually, you don't need to use them directly, but if you need extra performance, you can access them directly.
-
-### Async gRPC
+Starting from version 1.6.1, all python client methods are available in async version.
 
-Example of using raw async gRPC client:
+To use it, just import `AsyncQdrantClient` instead of `QdrantClient`:
 
 ```python
-from qdrant_client import QdrantClient, grpc
+from qdrant_client import AsyncQdrantClient, models
+import numpy as np
+import asyncio
+
+async def main():
+    # Your async code using QdrantClient might be put here
+    client = AsyncQdrantClient(url="http://localhost:6333")
+
+    await client.create_collection(
+        collection_name="my_collection",
+        vectors_config=models.VectorParams(size=10, distance=models.Distance.COSINE),
+    )
+
+    await client.upsert(
+        collection_name="my_collection",
+        points=[
+            models.PointStruct(
+                id=i,
+                vector=np.random.rand(10).tolist(),
+            )
+            for i in range(100)
+        ],
+    )
 
-client = QdrantClient(prefer_grpc=True, timeout=3.0)
+    res = await client.search(
+        collection_name="my_collection",
+        query_vector=np.random.rand(10).tolist(),  # type: ignore
+        limit=10,
+    )
 
-grpc_collections = client.async_grpc_collections
+    print(res)
 
-res = await grpc_collections.List(grpc.ListCollectionsRequest(), timeout=1.0)
+asyncio.run(main())
 ```
 
+Both, gRPC and REST API are supported in async mode.
 More examples can be found [here](./tests/test_async_qdrant_client.py).
 
 ### Development

docs/source/conf.py

@@ -32,6 +32,8 @@
     "sphinx.ext.autodoc",
     "sphinx.ext.viewcode",
     "sphinx.ext.intersphinx",
+    "nbsphinx",
+    "IPython.sphinxext.ipython_console_highlighting"
 ]
 
 # prevents sphinx from adding full path to type hints
@@ -68,6 +70,8 @@
 # This pattern also affects html_static_path and html_extra_path.
 exclude_patterns = [
     "*qdrant_openapi_client*",
+    "*grpc*",
+    "*tests*" # tests are not part of the documentation
 ]
 # -- Options for HTML output -------------------------------------------------