datachain 0.3.1__tar.gz → 0.3.3__tar.gz

{datachain-0.3.1 → datachain-0.3.3}/.github/workflows/benchmarks.yml

@@ -5,23 +5,24 @@ on:
     - cron: '0 0 * * *'
   pull_request:
     types: [opened, reopened, labeled, synchronize]
-  workflow_dispatch: {}
+  workflow_dispatch:
 
 env:
   FORCE_COLOR: "1"
 
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
-  build:
-    if: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'run-benchmarks') }}
+  run:
     runs-on: ubuntu-latest
-
     steps:
       - uses: actions/checkout@v4
-
-      - name: Set up Python 3.10
+      - name: Set up Python 3.12
         uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.12'
           cache: 'pip'
 
       - name: Upgrade nox and uv
@@ -30,5 +31,7 @@ jobs:
           nox --version
           uv --version
 
+      - run: uv pip install dvc[gs] --system
+      - run: dvc --cd tests/benchmarks/datasets pull
       - name: Run benchmarks
         run: nox -s bench

datachain-0.3.3/.github/workflows/tests-studio.yml

@@ -0,0 +1,103 @@
+name: Studio Tests
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+  workflow_dispatch:
+
+env:
+  FORCE_COLOR: "1"
+  BRANCH: ${{ github.head_ref || github.ref_name }}
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  studio:
+    if: '!github.event.pull_request.head.repo.fork'
+    runs-on: ubuntu-latest-16-cores
+    strategy:
+      matrix:
+        pyv: ['3.12']
+        group: [1, 2, 3, 4, 5, 6]
+    services:
+      postgres:
+        image: postgres:16.3
+        ports:
+          - 5432:5432
+        env:
+          POSTGRES_USER: test
+          POSTGRES_DB: database
+          POSTGRES_HOST_AUTH_METHOD: trust
+      clickhouse:
+        image: clickhouse/clickhouse-server:24
+        ports:
+          - 8123:8123
+          - 9010:9000
+        env:
+          CLICKHOUSE_DB: studio_local_db
+          CLICKHOUSE_USER: studio_local
+          CLICKHOUSE_PASSWORD: ch123456789!
+          CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT: 1
+      redis:
+        image: redis:7.2.5
+        ports:
+          - 6379:6379
+    steps:
+      - name: Studio branch name
+        env:
+          BRANCH: ${{ env.BRANCH }}
+          STUDIO_READ_ACCESS_TOKEN: ${{ secrets.ITERATIVE_STUDIO_READ_ACCESS_TOKEN }}
+        run: |
+          echo "DataChain branch: $BRANCH"
+          if [[ "$BRANCH" == "main" ]]
+          then
+              STUDIO_BRANCH=develop
+          elif git ls-remote --heads https://"$STUDIO_READ_ACCESS_TOKEN"@github.com/iterative/studio.git "$BRANCH" | grep -F "$BRANCH" 2>&1>/dev/null
+          then
+              STUDIO_BRANCH="$BRANCH"
+          else
+              STUDIO_BRANCH=develop
+          fi
+          echo "STUDIO_BRANCH=$STUDIO_BRANCH" >> $GITHUB_ENV
+          echo "Studio branch: $STUDIO_BRANCH"
+
+      - name: Check out Studio
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          repository: iterative/studio
+          ref: ${{ env.STUDIO_BRANCH }}
+          token: ${{ secrets.ITERATIVE_STUDIO_READ_ACCESS_TOKEN }}
+
+      - name: Check out repository
+        uses: actions/checkout@v4
+        with:
+          path: './backend/datachain'
+          fetch-depth: 0
+
+      - name: Set up Python ${{ matrix.pyv }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.pyv }}
+          cache: 'pip'
+
+      - name: Install uv
+        run: |
+          python -m pip install --upgrade uv
+          uv --version
+
+      - name: Install dependencies
+        run: uv pip install --system ./backend/datachain_server[tests] ./backend/datachain[tests]
+
+      - name: Run tests
+        # Generate `.test_durations` file with `pytest --store-durations --durations-path ../.github/.test_durations ...`
+        run: >
+          pytest
+          --config-file=pyproject.toml -rs
+          --splits=6 --group=${{ matrix.group }} --durations-path=../../.github/.test_durations
+          -m 'not benchmark'
+          tests ../datachain/tests
+        working-directory: backend/datachain_server

{datachain-0.3.1 → datachain-0.3.3}/.github/workflows/tests.yml

@@ -8,7 +8,6 @@ on:
 
 env:
   FORCE_COLOR: "1"
-  BRANCH: ${{ github.head_ref || github.ref_name }}
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
@@ -18,7 +17,6 @@ jobs:
   lint:
     runs-on: ubuntu-latest
     steps:
-
       - name: Check out the repository
         uses: actions/checkout@v4
         with:
@@ -112,70 +110,17 @@ jobs:
       - name: Build docs
         run: nox -s docs
 
-
-  studio:
-    if: '!github.event.pull_request.head.repo.fork'
-    runs-on: ubuntu-latest-16-cores
+  examples:
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 60
     strategy:
+      fail-fast: false
       matrix:
-        pyv: ['3.12']
-        group: [1, 2, 3, 4, 5, 6]
-    services:
-      postgres:
-        image: postgres:16.3
-        ports:
-          - 5432:5432
-        env:
-          POSTGRES_USER: test
-          POSTGRES_DB: database
-          POSTGRES_HOST_AUTH_METHOD: trust
-      clickhouse:
-        image: clickhouse/clickhouse-server:24
-        ports:
-          - 8123:8123
-          - 9010:9000
-        env:
-          CLICKHOUSE_DB: studio_local_db
-          CLICKHOUSE_USER: studio_local
-          CLICKHOUSE_PASSWORD: ch123456789!
-          CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT: 1
-      redis:
-        image: redis:7.2.5
-        ports:
-          - 6379:6379
+        os: [ubuntu-latest-16-cores, macos-latest, windows-latest-8-cores]
+        pyv: ['3.9', '3.12']
+        group: ['get_started', 'llm_and_nlp or computer_vision', 'multimodal']
     steps:
-
-      - name: Studio branch name
-        env:
-          BRANCH: ${{ env.BRANCH }}
-          STUDIO_READ_ACCESS_TOKEN: ${{ secrets.ITERATIVE_STUDIO_READ_ACCESS_TOKEN }}
-        run: |
-          echo "DataChain branch: $BRANCH"
-          if [[ "$BRANCH" == "main" ]]
-          then
-              STUDIO_BRANCH=develop
-          elif git ls-remote --heads https://"$STUDIO_READ_ACCESS_TOKEN"@github.com/iterative/studio.git "$BRANCH" | grep -F "$BRANCH" 2>&1>/dev/null
-          then
-              STUDIO_BRANCH="$BRANCH"
-          else
-              STUDIO_BRANCH=develop
-          fi
-          echo "STUDIO_BRANCH=$STUDIO_BRANCH" >> $GITHUB_ENV
-          echo "Studio branch: $STUDIO_BRANCH"
-
-      - name: Check out Studio
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-          repository: iterative/studio
-          ref: ${{ env.STUDIO_BRANCH }}
-          token: ${{ secrets.ITERATIVE_STUDIO_READ_ACCESS_TOKEN }}
-
-      - name: Check out repository
-        uses: actions/checkout@v4
-        with:
-          path: './backend/datachain'
-          fetch-depth: 0
+      - uses: actions/checkout@v4
 
       - name: Set up Python ${{ matrix.pyv }}
         uses: actions/setup-python@v5
@@ -183,19 +128,11 @@ jobs:
           python-version: ${{ matrix.pyv }}
           cache: 'pip'
 
-      - name: Install uv
+      - name: Upgrade nox and uv
         run: |
-          python -m pip install --upgrade uv
+          python -m pip install --upgrade 'nox[uv]'
+          nox --version
           uv --version
 
-      - name: Install dependencies
-        run: uv pip install --system ./backend/datachain_server[tests] ./backend/datachain[tests]
-
-      - name: Run tests
-        # Generate `.test_durations` file with `pytest --store-durations --durations-path ../.github/.test_durations ...`
-        run: >
-          pytest
-          --config-file=pyproject.toml -rs
-          --splits=6 --group=${{ matrix.group }} --durations-path=../../.github/.test_durations
-          tests ../datachain/tests
-        working-directory: backend/datachain_server
+      - name: Run examples
+        run: nox -s examples -p ${{ matrix.pyv }} -- -m "${{ matrix.group }}"

{datachain-0.3.1 → datachain-0.3.3}/.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.5.6'
+    rev: 'v0.5.7'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

{datachain-0.3.1/src/datachain.egg-info → datachain-0.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: datachain
-Version: 0.3.1
+Version: 0.3.3
 Summary: Wrangle unstructured AI data at scale
 Author-email: Dmitry Petrov <support@dvc.org>
 License: Apache-2.0
@@ -76,11 +76,20 @@ Requires-Dist: aiotools>=1.7.0; extra == "tests"
 Requires-Dist: requests-mock; extra == "tests"
 Provides-Extra: dev
 Requires-Dist: datachain[docs,tests]; extra == "dev"
-Requires-Dist: mypy==1.10.1; extra == "dev"
+Requires-Dist: mypy==1.11.1; extra == "dev"
 Requires-Dist: types-python-dateutil; extra == "dev"
 Requires-Dist: types-pytz; extra == "dev"
 Requires-Dist: types-PyYAML; extra == "dev"
 Requires-Dist: types-requests; extra == "dev"
+Provides-Extra: examples
+Requires-Dist: datachain[tests]; extra == "examples"
+Requires-Dist: numpy<2,>=1; extra == "examples"
+Requires-Dist: defusedxml; extra == "examples"
+Requires-Dist: accelerate; extra == "examples"
+Requires-Dist: unstructured[pdf]; extra == "examples"
+Requires-Dist: pdfplumber==0.11.3; extra == "examples"
+Requires-Dist: huggingface_hub[hf_transfer]; extra == "examples"
+Requires-Dist: nltk==3.8.1; extra == "examples"
 
 |PyPI| |Python Version| |Codecov| |Tests|
 
@@ -100,102 +109,78 @@ Requires-Dist: types-requests; extra == "dev"
 AI 🔗 DataChain
 ----------------
 
-DataChain is a data-frame library designed for AI-specific scenarios. It helps ML and
-AI engineers build a metadata layer on top of unstructured files and analyze data using
-this layer.
+DataChain is a modern Pythonic data-frame library designed for artificial intelligence.
+It is made to organize your unstructured data into datasets and wrangle it at scale on
+your local machine.
 
-📂 **Raw Files Processing**
-   Process raw files (images, video, text, PDFs) directly from storage (S3, GCP, Azure,
-   Local), version and update datasets.
+Key Features
+============
 
-🌟 **Metadata layer.**
-   Build a metadata layer on top of files using structured sources like CSV, Parquet,
-   and JSON files.
+📂 **Storage as a Source of Truth.**
+   - Process unstructured data without redundant copies: S3, GCP, Azure, and local
+     file systems.
+   - Multimodal data: images, video, text, PDFs, JSONs, CSVs, parquet.
+   - Join files and metadata together into persistent, versioned, columnar datasets.
 
-⭐ **Metadata enrichment.**
-   Enhance the metadata layer with outputs from local ML model inferences and LLM calls.
+🐍 **Python-friendly data pipelines.**
+   - Operate on Python objects and object fields.
+   - Built-in parallelization and out-of-memory compute without a need in SQL or
+     Spark jobs.
 
-🛠️ **Data Transformation.**
-   Transform metadata using traditional methods like filtering, grouping, joining, and
-   others.
+🧠 **Data Enrichment and Processing.**
+   - Generate metadata columns using local AI models and LLM APIs.
+   - Filter, join, and group by AI metadata. Vector similarity search.
+   - Pass datasets to Pytorch and Tensorflow, or export back into storage.
 
-🐍 **User-friendly interface.**
-   Operate efficiently with familiar Python objects and object fields, eliminating the
-   need for SQL.
+🚀 **Efficiency.**
+   - Parallelization, out-of-memory workloads and data caching.
+   - Vectorized operations on Python object fields: sum, count, avg, etc.
+   - Vector search on embeddings.
 
 
+Quick Start
+-----------
+
 .. code:: console
 
    $ pip install datachain
 
 
-Data Structures
-===============
-
-DataChain introduces expressive data structures tailored for AI-specific workload:
-
-- **Dataset:** Preserves the file-references and meta-information. Takes care of Python
-  object serialization, dataset versioning and difference. Operations on dataset:
-
-  - **Transformations:** traditional data-frame or SQL operations such as filtering,
-    grouping, joining.
-  - **Enrichments:** mapping, aggregating and generating using customer’s Python
-    code. This is needed to work with ML inference and LLM calls.
-
-- **Chain** is a sequence of operations on datasets. Chain executes operations in lazy
-  mode - only when needed.
-
-DataChain name comes from these major data structures: dataset and chaining.
-
+Selecting files using JSON metadata
+======================================
 
-What’s new in DataChain?
-========================
+A storage consists of images of cats and dogs (`dog.1048.jpg`, `cat.1009.jpg`),
+annotated with ground truth and model inferences in the 'json-pairs' format,
+where each image has a matching JSON file like `cat.1009.json`:
 
-The project combines multiple ideas from different areas in order to simplify AI
-use-cases and at the same time to fit it into traditional data infrastructure.
+.. code:: json
 
-- **Python-Native for AI.** Utilizes Python instead of SQL for data manipulation as the
-  native language for AI. It’s powered by `Pydantic`_ data models.
-- **Separation of CPU-GPU workloads.** Distinguishes CPU-heavy transformations (filter,
-  group_by, join) from GPU heavy enrichments (ML-inference or LLM calls). That’s mostly
-  needed for distributed computations.
-- **Resuming data processing** (in development). Introduces idempotent operations,
-  allowing data processing to resume from the last successful process file/record/batch
-  if it fails due to issues like failed LLM calls, ML inference or file download.
+    {
+        "class": "cat", "id": "1009", "num_annotators": 8,
+        "inference": {"class": "dog", "confidence": 0.68}
+    }
 
-Additional relatively new ideas:
+Example of downloading only high-confidence cat images using JSON metadata:
 
-- **Functional style data processing.** Using a functional/chaining approach to data
-  processing rather than declarative SQL, inspired by R-dplyr and some Python libraries.
-- **Data Versioning.** Treats raw files in cloud storage as the source of truth for data
-  and implements data versioning, extending ideas from DVC (developed by the same team).
 
+.. code:: py
 
-What DataChain is NOT?
-======================
-
-- **Not a database** (Postgres, MySQL). Instead, it uses databases under the hood:
-  `SQLite`_ in open-source and ClickHouse and other data warehouses for the commercial
-  version.
-- **Not a data processing tool / data warehouse** (Spark, Snowflake, Big Query) since
-  it delegates heavy data transformations to underlying data warehouses and focuses on
-  AI specific data enrichments and orchestrating all the pieces together.
-
+    from datachain import Column, DataChain
 
-Quick Start
------------
+    meta = DataChain.from_json("gs://datachain-demo/dogs-and-cats/*json", object_name="meta")
+    images = DataChain.from_storage("gs://datachain-demo/dogs-and-cats/*jpg")
 
-Data curation with a local model
-=================================
+    images_id = images.map(id=lambda file: file.path.split('.')[-2])
+    annotated = images_id.merge(meta, on="id", right_on="meta.id")
 
-We will evaluate chatbot dialogs stored as text files in Google Cloud Storage
-- 50 files total in this example.
-These dialogs involve users chatting with a bot while looking for better wireless plans.
-Our goal is to identify the successful dialogs.
+    likely_cats = annotated.filter((Column("meta.inference.confidence") > 0.93) \
+                                   & (Column("meta.inference.class_") == "cat"))
+    likely_cats.export_files("high-confidence-cats/", signal="file")
 
-The data used in the examples is `publicly available`_. The sample code is designed to run on a local machine.
 
-First, we'll show batch inference with a simple sentiment model using the `transformers` library:
+Data curation with a local AI model
+===================================
+Batch inference with a simple sentiment model using the `transformers` library:
 
 .. code:: shell
 
@@ -246,30 +231,30 @@ LLM judging chatbots
 =============================
 
 LLMs can work as efficient universal classifiers. In the example below,
-we employ a free API from Mistral to judge the chatbot performance. Please get a free
+we employ a free API from Mistral to judge the `publicly available`_ chatbot dialogs. Please get a free
 Mistral API key at https://console.mistral.ai
 
+
 .. code:: shell
 
-    $ pip install mistralai
+    $ pip install mistralai (Requires version >=1.0.0)
     $ export MISTRAL_API_KEY=_your_key_
 
 DataChain can parallelize API calls; the free Mistral tier supports up to 4 requests at the same time.
 
 .. code:: py
 
-    from mistralai.client import MistralClient
-    from mistralai.models.chat_completion import ChatMessage
+    from mistralai import Mistral
     from datachain import File, DataChain, Column
 
     PROMPT = "Was this dialog successful? Answer in a single word: Success or Failure."
 
     def eval_dialogue(file: File) -> bool:
-         client = MistralClient()
-         response = client.chat(
+         client = Mistral()
+         response = client.chat.complete(
              model="open-mixtral-8x22b",
-             messages=[ChatMessage(role="system", content=PROMPT),
-                       ChatMessage(role="user", content=file.read())])
+             messages=[{"role": "system", "content": PROMPT},
+                       {"role": "user", "content": file.read()}])
          result = response.choices[0].message.content
          return result.lower().startswith("success")
 
@@ -309,8 +294,8 @@ Instead of extracting this information from the Mistral response data structure
 
 .. code:: py
 
-    from mistralai.client import MistralClient
-    from mistralai.models.chat_completion import ChatMessage, ChatCompletionResponse
+    from mistralai import Mistral
+    from mistralai.models import ChatCompletionResponse
     from datachain import File, DataChain, Column
 
     PROMPT = "Was this dialog successful? Answer in a single word: Success or Failure."
@@ -319,8 +304,8 @@ Instead of extracting this information from the Mistral response data structure
          client = MistralClient()
          return client.chat(
              model="open-mixtral-8x22b",
-             messages=[ChatMessage(role="system", content=PROMPT),
-                       ChatMessage(role="user", content=file.read())])
+             messages=[{"role": "system", "content": PROMPT},
+                       {"role": "user", "content": file.read()}])
 
     chain = (
        DataChain.from_storage("gs://datachain-demo/chatbot-KiT/", object_name="file")
@@ -438,7 +423,10 @@ Tutorials
 ---------
 
 * `Getting Started`_
-* `Multimodal <examples/multimodal/clip_fine_tuning.ipynb>`_ (try in `Colab <https://colab.research.google.com/github/iterative/datachain/blob/main/examples/multimodal/clip_fine_tuning.ipynb>`__)
+* `Multimodal <https://github.com/iterative/datachain-examples/blob/main/multimodal/clip_fine_tuning.ipynb>`_ (try in `Colab <https://colab.research.google.com/github/iterative/datachain-examples/blob/main/multimodal/clip_fine_tuning.ipynb>`__)
+* `LLM evaluations <https://github.com/iterative/datachain-examples/blob/main/llm/llm_chatbot_evaluation.ipynb>`_ (try in `Colab <https://colab.research.google.com/github/iterative/datachain-examples/blob/main/llm/llm_chatbot_evaluation.ipynb>`__)
+* `Reading JSON metadata <https://github.com/iterative/datachain-examples/blob/main/formats/json-metadata-tutorial.ipynb>`_ (try in `Colab <https://colab.research.google.com/github/iterative/datachain-examples/blob/main/formats/json-metadata-tutorial.ipynb>`__)
+
 
 Contributions
 -------------