The AI Toolchain — issue -403, April 29, 2022

Triton v2.21.0 adds raw binary requests, custom metrics via C API, multi-cloud model repos, and ensemble optional inputs.

$ git clone --branch v2.21.0 https://github.com/triton-inference-server/server.git
# already have the repo? check out this version:
$ git checkout v2.21.0

• ›Adds --tmp-dir argument to build.py to specify a custom temporary directory during container builds.
• ›Supports raw binary HTTP requests to the inference endpoint, eliminating the need to specify an inference header.
• ›Adds custom metrics support via the Triton C API, allowing custom backends and applications to publish metrics to the existing Triton metrics endpoint.
• ›Supports loading models from multiple cloud storage repositories simultaneously — including multiple S3 buckets, GCS buckets, and Azure Storage containers — in a single Triton instance.
• ›Ensembles now recognize optional inputs, enabling more flexible ensemble pipeline configurations.

Zed v0.31.0 adds format_on_save setting, redesigned status bar panel toggles, and grouped theme switcher.

$ git clone --branch v0.31.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.31.0

• ›Adds format_on_save setting to allow disabling automatic formatting on save.
• ›Panels can now be toggled via icons in the status bar, replacing the sidebar.
• ›Titlebar now displays open folder names; project diagnostics status is surfaced in the status bar.
• ›Theme switcher now groups themes by light and dark.
• ›Multi-buffer refactoring results are now sorted alphabetically by path.

$ git clone --branch v0.30.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.30.0

[
    {
        "context": "Editor",
        "bindings": {
            "ctrl-w": "editor::DeleteToPreviousWordStart"
        }
    },
    {
        "context": "Workspace",
        "bindings": {
            "f1": "zed::OpenKeymap"
        }
    }
]

$ git clone --branch v0.29.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.29.0

$ git clone --branch v0.28.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.28.0

$ git clone --branch v0.26.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.26.0

{
  "Editor": {
    "ctrl-w": "editor::DeleteToPreviousWordStart"
  }
}

$ git clone --branch v0.25.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.25.0

$ git clone --branch v0.24.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.24.0

Qdrant v0.7.0 adds arbitrary JSON payloads, new Bool/IsEmpty/ValuesCount filters, Alias API in gRPC, and order-of-magnitude faster Euclidean distance via SIMD.

$ git clone --branch v0.7.0 https://github.com/qdrant/qdrant.git
# already have the repo? check out this version:
$ git checkout v0.7.0

• ›Adds IsEmpty filter condition to match fields with no value set.
• ›Adds ValuesCount filter condition to match fields based on the number of values they contain.
• ›Adds Bool filter support and refactors the Match condition for payload filtering.
• ›Adds Alias API to gRPC, bringing it to parity with the REST API.
• ›Supports arbitrary JSON as payload — uploaded payload structure now exactly matches retrieved results, and the payload schema is used for field indexes only.

Weaviate v1.12.0 adds configurable stopword lists, unlimited certainty-based vector search, a Shard API, and disk-pressure auto-protection.

$ git clone --branch v1.12.0 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout v1.12.0

• ›Adds Shard API to expose individual shard status and allow marking shards as read-only via the API, blocking writes while permitting reads.
• ›Introduces two configurable disk-pressure thresholds: a warning threshold (e.g. 80%) that logs alerts, and a critical threshold (e.g. 90%) that automatically marks all shards on the affected node as read-only.
• ›Enables unlimited vector search by certainty, returning all results within the desired certainty range regardless of internal limits, with a configurable global maximum to prevent out-of-memory conditions.
• ›Adds support for turning off tokenization on string fields so the entire field — including spaces — is indexed as a single token, preventing unwanted partial-string matches.
• ›Introduces a fully configurable inverted-index stopword list, applicable to exact-match queries now and in anticipation of upcoming BM25 and mixed BM25/dense-vector search support.