Backfill issue -404 — The AI Toolchain

EDITIONS tail grep head diff uniq

The daily firehose — everything the toolchain shipped today, already filtered.

// HOW THIS ISSUE IS MADE

We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.

VIEW

ISSUE VIEW full issue

Do you prefer this view?

$ tct list   # 5 tools matched

AI & LLM Tooling

◆ AI Agent Frameworks

deepset Haystack

v1.3.0 NOTES

Haystack v1.3.0 adds PineconeDocumentStore, BEIR benchmarking integration, YAML pipeline validation, and new RouteDocuments/JoinAnswers nodes.

└──▷ GET THIS VERSION

$ git clone --branch v1.3.0 https://github.com/deepset-ai/haystack.git
# already have the repo? check out this version:
$ git checkout v1.3.0

└──▷ USE IT

Validate a pipeline YAML file before deployment to catch misconfigured components early in CI.

python

from pathlib import Path
from haystack.pipelines.config import validate_yaml
validate_yaml(Path('rest_api/pipeline/pipelines.haystack-pipeline.yml'))

Connect to Pinecone's managed vector database as a DocumentStore for large-scale dense retrieval without self-hosting infrastructure.

python

import os
from haystack.document_stores import PineconeDocumentStore
document_store = PineconeDocumentStore(api_key=os.environ['PINECONE_API_KEY'])

Benchmark a retrieval pipeline against the BEIR 'scifact' dataset for zero-shot evaluation of retrieval quality.

python

from haystack.pipelines import DocumentSearchPipeline, Pipeline
from haystack.nodes import ElasticsearchRetriever
from haystack.document_stores.elasticsearch import ElasticsearchDocumentStore

document_store = ElasticsearchDocumentStore(search_fields=['content', 'name'], index='scifact_beir')
retriever = ElasticsearchRetriever(document_store=document_store, top_k=1000)
query_pipeline = DocumentSearchPipeline(retriever=retriever)

ndcg, _map, recall, precision = Pipeline.eval_beir(
    index_pipeline=index_pipeline, query_pipeline=query_pipeline, dataset='scifact'
)

›Adds validate_yaml(Path(...)) from haystack.pipelines.config to programmatically validate pipeline YAML files, identifying erroneous components and parameters.
›Adds PineconeDocumentStore to haystack.document_stores, backed by Pinecone's managed vector database for large-scale dense retrieval; requires only a PINECONE_API_KEY.
›Adds Pipeline.eval_beir() for zero-shot benchmarking of retrieval pipelines against BEIR datasets in 17 languages; available via pip install farm-haystack[beir].
›Adds RouteDocuments and JoinAnswers pipeline nodes to haystack.nodes.
›Adds deploy and undeploy support for Pipelines on Deepset Cloud.

+4 moreshow less

›Adds *.haystack-pipeline.yml file suffix convention enabling IDE schema validation and autocompletion via SchemaStore; schema published at https://raw.githubusercontent.com/deepset-ai/haystack/master/haystack/json-schemas/haystack-pipeline.schema.json.
›Supports version: 'unstable' in pipeline YAML files to bypass schema validation.
›Reintroduces debug as a valid global key in Pipeline params.
›Adds bulk insert support to SQL DocumentStores.

└──▷ BREAKING ON UPGRADE

!Milvus2DocumentStore now requires pymilvus>=2.0.0; setups using older pymilvus versions will break.
!The device parameter in internal methods is now a torch.device; code passing plain strings for device in affected onnxruntime paths may break.

Was this useful?

◆ AI Model & Data Infrastructure

NVIDIA Triton Inference Server

v2.20.0 NOTES

Triton v2.20.0 adds ragged batching for ONNX/TensorRT/TF, cache-miss Prometheus metrics, and trace config via API.

└──▷ GET THIS VERSION

$ git clone --branch v2.20.0 https://github.com/triton-inference-server/server.git
# already have the repo? check out this version:
$ git checkout v2.20.0

›Adds cache miss statistics to the Prometheus metrics endpoint, as documented in the metrics reference.
›Enables trace settings to be configured at runtime via the Triton Server Trace Protocol extension.
›Supports loading models from a serialized model_config message via the Triton Server model-repository API.
›ONNX Runtime, TensorRT, and TensorFlow backends now support server-side, multi-dimensional ragged batching.

Was this useful?

◆ AI Coding Agents

Zed

v0.23.0 6 RELEASES · 2022-03-02 → 2022-03-27 NOTES STABLE

Zed v0.23.0 adds sub-word movement/deletion bindings and improves collaborative editing reconnect handling.

└──▷ GET THIS VERSION

$ git clone --branch v0.23.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.23.0

›Adds ctrl-modified bindings for sub-word movement and deletion, respecting camelCase and snake_case boundaries.
›Improves host reconnect experience in collaborative sessions: guests visually disappear on connection loss and sharing can resume on reconnect.
›Unfolds folded regions automatically when selecting a search match or using cmd-d.

5 more releases in this issue · 2022-03-02 → 2022-03-27

v0.22.0 NOTES STABLE

Zed v0.22.0 adds real-time collaborator following and new pane-focus keybindings.

└──▷ GET THIS VERSION

$ git clone --branch v0.22.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.22.0

›Adds collaborator following: click a collaborator's avatar in the titlebar to follow them, syncing your pane to their focused view in real time; disengage by typing, scrolling, or moving the cursor.
›Adds ctrl-alt-cmd-f keybinding to cycle between following different collaborators.
›Supports following multiple collaborators simultaneously in separate panes.
›Adds cmd-k cmd-right and cmd-k cmd-left keybindings for focusing the next and previous pane, respectively.

v0.21.0 NOTES STABLE

Zed v0.21.0 adds jump-to-previous-diagnostic via shift-f8 and improved diagnostic rendering.

└──▷ GET THIS VERSION

$ git clone --branch v0.21.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.21.0

›Adds shift-f8 keybinding to jump to the previous diagnostic in the editor.
›Improves rendering of diagnostics that indicate unnecessary code.

v0.20.0 NOTES STABLE

Zed v0.20.0 adds a settings file, language server status in the status bar, and improved rename workflows.

└──▷ GET THIS VERSION

$ git clone --branch v0.20.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.20.0

└──▷ USE IT

Persist your Zed configuration across sessions by editing the new settings file.

json

~/.zed/settings.json

›Adds ~/.zed/settings.json as a persistent settings file for configuring Zed.
›Displays the status of running language servers in the status bar.
›Pressing F2 to rename a variable now selects the new name and dims all instances of the old name.
›Typing an opening bracket with text selected now surrounds the selection with brackets.

v0.19.0 NOTES STABLE

Zed v0.19.0 adds JSON language server support, improved connection reliability, and new tab management shortcut.

└──▷ GET THIS VERSION

$ git clone --branch v0.19.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.19.0

›Supports closing other tabs via cmd-alt-w.
›Adds JSON language server capabilities including diagnostics and syntax highlighting.
›Automatically removes stale peers from shared projects upon disconnection.
›Introduces refined bundled fonts.

v0.18.0 NOTES STABLE

Zed v0.18.0 adds project-wide search with result cycling via keyboard shortcuts.

└──▷ GET THIS VERSION

$ git clone --branch v0.18.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.18.0

›Adds project-wide text search triggered by cmd-shift-f, with enter to search and cmd-enter to open results in a new tab.
›Supports cycling through project search results using cmd-g (next) and cmd-shift-g (previous).

Was this useful?

Other / Uncategorized

◆ VECTOR DB RAG

Qdrant

v0.6.0 NOTES

Qdrant v0.6.0 adds gRPC support for all endpoints and enriches recommend responses with payload and vector data.

└──▷ GET THIS VERSION

$ git clone --branch v0.6.0 https://github.com/qdrant/qdrant.git
# already have the repo? check out this version:
$ git checkout v0.6.0

›Adds gRPC support for all endpoints, with Protobuf docs and a configuration guide to enable it.
›The recommend endpoint can now return payload and vector alongside results.

└──▷ BREAKING ON UPGRADE

!Python client users must follow migration examples at https://github.com/qdrant/qdrant_client/releases/tag/v0.6.0 — the REST API itself is compatible, but the Python client interface has changed.

Was this useful?

Weaviate

v1.11.0 NOTES

Weaviate v1.11.0 lets you supply your OpenAI API key at query time instead of storing it server-side.

└──▷ GET THIS VERSION

$ git clone --branch v1.11.0 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout v1.11.0

›Enables passing the OpenAI API key at query time via the text2vec-openai module, avoiding the need to store third-party credentials on the server.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · March 29, 2022
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -404, March 29, 2022

deepset Haystack

NVIDIA Triton Inference Server

Zed

Qdrant

Weaviate