Commit Graph

8 Commits

Author SHA1 Message Date
George Panchuk
698db1d33f new: drop python3.9, replace union and optional with | where possible 2025-11-14 03:20:36 +07:00
George
200020f19a wip: builtin bm25 support (#1060)
* wip: builtin bm25 support

* remove debug print

* new: add builtin embedder, add server version check for inference

* fix: regen async

* fix: fix fastembed import

* fix: regen async

* tests: add tests for builtin inference

* fix: fix fastembed checks, improve exceptions
2025-09-15 16:18:41 +08:00
George
42856424a6 new: move fastembed imports and constants into a class to support cus… (#994)
* new: move fastembed imports and constants into a class to support custom models and improve exceptions

* new: add is_supported model to FastEmbedMisc

* fix: fix types
2025-05-20 14:46:18 +04:00
George
a0bbadaa08 new: support multimodal embeddings (#908)
* new: support multimodal embeddings

* fix: fix embed when model name is present in both text and image supported models

* fix: fix type checkers

* refactor: split multimodal embed into embed text and embed image

* chore: comment batch separation

* chore: rollback formatting
2025-04-15 18:11:33 +03:00
George
5c2f3e883c Remove multitask models list (#945)
* new: remove multitask embedding list

* new: update fastembed
2025-04-15 16:43:06 +03:00
George
ce4c51dd3c Default inference batch size (#907)
* fix: fix inference batch size propagation

* fix: propagate batch size to embed worker

* fix: fix type ignore comment

* fix: replace mocking class method with object method

* fix: add missing inference batch size

* fix: fix batch size propagation to worker
2025-02-21 12:47:57 +01:00
Hossam Hagag
5cd7538fd8 propagate task_id for multitask models in local inference
* tests: Updated propagate options test

* fix: Fix CI

* fix: Fix ci

* revert test

* new: update task id propagation

---------

Co-authored-by: George Panchuk <george.panchuk@qdrant.tech>
2025-02-19 13:52:49 +01:00
George
b4ae703d1b Local inference upload collection and upload records (#862)
* wip: add draft implementation of batch processing

* fix: embed dict and list of docs, remove redundant code

* new: regen async, small refactor

* refactor: add docstrings, rename methods

* Upload points local inference (#881)

* new: separate single and plural model embeddings

* fix: fix lazy embed models

* new: add inference object inspections to upload methods

* wip: local inference upload parallel

* new: add local inference to upload points and upload collection, refactor mixin

* fix: remove redundant code

* redundant import

* tests: check is query for query points batch

* refactor: refactor semi ordered map

* tests: add test for local inference with batches with docs and vectors

* tests: check the order of dict processing

* new: distinguish models by options

* fix: fix typing

* fix: fix types

* new: embed batches with different options

* tests: add tests for batch with different options

* fix: ignore ide incorrect type inspection

* tests: wait for points to be inserted

* fix: set threads to 1 in parallel inference

* new: adjust max internal batch size

* fix: fix type hints

* function to get embeddings size (#892)

* function to get embeddings size

* async client

* keep sync

* new: extend embedding size to support image and late interaction models

---------

Co-authored-by: George Panchuk <george.panchuk@qdrant.tech>

* new: add local inference batch size (#894)

---------

Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
2025-01-29 15:53:24 +01:00