Backfill issue -396 — 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

v1.11.0 NOTES

Haystack v1.11.0 adds CohereEmbeddingEncoder, headline extraction from Markdown/PDF, TextIndexingPipeline, and document_store parameter on all retrievers.

└──▷ GET THIS VERSION

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

└──▷ USE IT

Extract structured headlines (with position and level) from a Markdown file when indexing, so downstream components can use document structure.

python

from haystack.nodes import MarkdownConverter

converter = MarkdownConverter(extract_headlines=True)
docs = converter.convert(file_path="report.md", meta=None)
print(docs[0].meta['headlines'])
# [{'headline': 'Introduction', 'start_idx': 0, 'level': 1}, ...]

Pass a specific document store at query time instead of at retriever construction, enabling a single retriever instance across multiple stores.

python

results = retriever.retrieve(
    query="What is the capital of France?",
    document_store=alternate_document_store
)

›Adds CohereEmbeddingEncoder to EmbeddingRetriever, supporting Cohere models small, medium, and large for document and query embeddings via API key.
›Adds extract_headlines parameter to MarkdownConverter and ParsrConverter; extracted headlines are stored in document.meta['headlines'] as a list of dicts with headline, start_idx, and level fields.
›Adds document_store parameter to all BaseRetriever.retrieve() and BaseRetriever.retrieve_batch() implementations, allowing the document store to be specified at query time.
›Introduces TextIndexingPipeline for straightforward text indexing workflows.
›Adds __contains__ method to Span for membership testing.

+2 moreshow less

›Adds exponential backoff decorator applied to OpenAI requests to handle rate limiting automatically.
›Adds indexing pipeline type support.

└──▷ BREAKING ON UPGRADE

!Milvus1DocumentStore is removed; Milvus versions below 2.x are no longer supported. Milvus2DocumentStore has been renamed to MilvusDocumentStore — code referencing either old name will break.
!A duplicated meta name field that was previously added to document content before embedding in the update_embeddings workflow has been removed; embeddings generated before this change may differ.

Was this useful?

◆ AI Model & Data Infrastructure

NVIDIA Triton Inference Server

v2.28.0 2 RELEASES · 2022-11-02 → 2022-11-22 NOTES STABLE

Triton v2.28.0 adds TensorRT 8.5 UINT8 I/O, data-dependent dynamic shapes, and external execution environment paths.

└──▷ GET THIS VERSION

$ git clone --branch v2.28.0 https://github.com/triton-inference-server/server.git
# already have the repo? check out this version:
$ git checkout v2.28.0

└──▷ USE IT

Point the Python backend to an execution environment (e.g. a conda pack) stored outside the model directory.

yaml

parameters {
  key: "EXECUTION_ENV_PATH"
  value: { string_value: "/shared/envs/my_env.tar.gz" }
}

›Adds EXECUTION_ENV_PATH parameter in config.pbtxt to specify execution environment paths outside the model directory for the Python backend.
›Supports TensorRT 8.5 UINT8 input/output tensors.
›Supports TensorRT 8.5 'data dependent dynamic shapes' operators, including ONNX NMS and NonZero operations.
›Windows beta release adds ONNX Runtime 1.13.1 support with CPU, CUDA, and TensorRT execution providers.
›Windows beta release adds OpenVINO 2021.4 model support.

+1 moreshow less

›Windows beta release supports HTTP/REST and GRPC endpoints.

1 more release in this issue · 2022-11-02 → 2022-11-22

v2.27.0 NOTES STABLE

Triton 2.27.0 adds JAX model support, enhanced Server Wrapper API with decoupled model and tracing, and multi-model concurrent profiling in Model Analyzer.

└──▷ GET THIS VERSION

$ git clone --branch v2.27.0 https://github.com/triton-inference-server/server.git
# already have the repo? check out this version:
$ git checkout v2.27.0

›Adds multi-model concurrent profiling to Model Analyzer via Multi-Model Search Mode, enabling simultaneous profiling and analysis of multiple models.
›Enhances the Server Wrapper API to support decoupled model workflows and tracing, covering previously missing features.
›Adds an example demonstrating JAX model usage inside Python backend models.

Was this useful?

◆ AI Coding Agents

Zed

v0.65.2 4 RELEASES · 2022-11-02 → 2022-11-23 NOTES STABLE

Zed v0.65.2 adds Ruby/ERB code intelligence via SolarGraph, drag-and-drop in the project panel, and new terminal keybindings.

└──▷ GET THIS VERSION

$ git clone --branch v0.65.2 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.65.2

›Adds alt-left and alt-right keybindings to the terminal keymap.
›Adds code intelligence for Ruby via the SolarGraph language server.
›Adds support for ERB templates.
›Enables additional Rust assists provided by Rust Analyzer.
›Adds drag-and-drop support for files and folders within the project panel.

+1 moreshow less

›Adds the ability to drag files from the project panel into panes to open them.

3 more releases in this issue · 2022-11-02 → 2022-11-23

v0.64.0 NOTES STABLE

Zed v0.64.0 adds Ruby syntax highlighting and new Rust Analyzer assists.

└──▷ GET THIS VERSION

$ git clone --branch v0.64.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.64.0

›Adds syntax highlighting for Ruby files.
›Enables additional Rust assists provided by Rust Analyzer.

v0.63.4 NOTES STABLE

Zed v0.63.4 adds git diff hunk navigation commands and Rust let/else syntax highlighting.

└──▷ GET THIS VERSION

$ git clone --branch v0.63.4 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.63.4

›Adds Go To Hunk command (default keybind cmd-f8) and Go To Previous Hunk command (default keybind cmd-shift-f8) to navigate between git diff hunks in a file.
›Adds syntax highlighting support for let/else statements in Rust.

v0.62.4 NOTES STABLE

Zed v0.62.4 adds screen sharing during calls and tab-drag pane splitting.

└──▷ GET THIS VERSION

$ git clone --branch v0.62.4 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.62.4

›Adds screen-sharing support during calls: clicking the screen button in the titlebar lets collaborators who are following you see your screen when you switch to a window outside of Zed, automatically resuming Zed buffer follow when you return focus.
›Adds the ability to drag tabs onto the edges of panes to create new splits.

Was this useful?

Other / Uncategorized

◆ VECTOR DB RAG

Milvus

v2.2.0 NOTES

Milvus 2.2.0 adds RBAC, disk-based ANN search, bulk file insertion, query pagination, quota limits, and collection-level TTL.

└──▷ GET THIS VERSION

$ git clone --branch v2.2.0 https://github.com/milvus-io/milvus.git
# already have the repo? check out this version:
$ git checkout v2.2.0

└──▷ USE IT

Re-enable Time Travel after upgrading, since it is now off by default.

yaml

common:
  retentionDuration: 432000  # seconds; e.g. 5 days

›Adds common.retentionDuration parameter to manually enable Time Travel, which is now disabled by default to save disk usage.
›Introduces bulk insertion APIs to load entities from JSON files directly into Milvus collections at scale.
›Adds Role-Based Access Control (RBAC) to manage users, roles, and privileges — similar to traditional database access management.
›Introduces quota limitation mechanisms to cap ingestion rate, search rate, and other traffic, protecting against OOM and crash conditions — configurable via Quota and Limitation Configurations.
›Supports configuring Time to Live (TTL) at the collection level when creating or modifying a collection, replacing the previous cluster-only TTL.

+7 moreshow less

›Adds DiskANN, an SSD-resident Vamana graph-based ANNS algorithm (Beta), enabling large-scale vector search without loading the full index into memory — saving up to 10x memory.
›Introduces milvus-backup tool (Beta) for data backup and restore, usable as a command-line tool or API server.
›Supports offset and keyword filtering on search and query results to paginate large result sets across RPCs.
›Exposes the flush() API to let users force-seal a growing segment and sync it to object storage.
›Adds collection-level latency metrics for search, query, insertion, and deletion operations.
›Further optimizes BirdWatcher debug tool to connect to Milvus meta storage and inspect internal system state.
›Enforces that a collection can only be loaded if an index has been created on it, and indexes cannot be created after a collection is loaded.

└──▷ BREAKING ON UPGRADE

!Milvus 2.2.0 is not fully compatible with earlier releases due to refined metadata storage and normalized API usage — migration from 2.1.x requires following the official upgrade guides.
!Time Travel is disabled by default; to re-enable it, common.retentionDuration must be configured manually.
!A collection can only be loaded with an index already created on it; loading without an index is no longer allowed.
!Indexes cannot be created after a collection is loaded.
!A loaded collection must be released before dropping its index.
!Auto-flush is no longer triggered by SDK APIs such as num_entities() or create_index().

Was this useful?

Qdrant

v0.11.4 4 RELEASES · 2022-11-05 → 2022-11-25 NOTES STABLE

Qdrant v0.11.4 adds mmap-based HNSW storage and gRPC compression, cutting RAM requirements and network overhead.

└──▷ GET THIS VERSION

$ git clone --branch v0.11.4 https://github.com/qdrant/qdrant.git
# already have the repo? check out this version:
$ git checkout v0.11.4

›Adds mmap support for HNSW graph storage, allowing the index to be kept on disk rather than in RAM — especially beneficial for collections with many small vectors.
›Enables compression in the gRPC protocol, reducing bandwidth for large payload transfers over slow networks.
›Adds probabilistic search sampling that significantly improves search speed when using large limit values, enabling fast retrieval of large numbers of nearest vectors.
›Switches to compact, CPU cache-friendly storage for HNSW graph links, improving search speed, memory usage, and application startup time.

3 more releases in this issue · 2022-11-05 → 2022-11-25

v0.11.3 NOTES STABLE

Qdrant v0.11.3 adds a snapshot recovery API with distributed mode support.

└──▷ GET THIS VERSION

$ git clone --branch v0.11.3 https://github.com/qdrant/qdrant.git
# already have the repo? check out this version:
$ git checkout v0.11.3

›Adds an API for recovering snapshots, including support for recovery in distributed (multi-node) mode.

v0.11.2 NOTES STABLE

Qdrant v0.11.2 adds HTTP compression middleware and improved read-after-write consistency on replica failure.

└──▷ GET THIS VERSION

$ git clone --branch v0.11.2 https://github.com/qdrant/qdrant.git
# already have the repo? check out this version:
$ git checkout v0.11.2

›Enables HTTP compression middleware for the REST API, reducing bandwidth for large responses.
›Ensures read-after-write consistency when a replica fails and requests are routed to the same peer.
›Reduces RAM usage for the ID tracker, particularly beneficial for collections with many small vectors.

v0.11.1 NOTES STABLE

Qdrant v0.11.1 enables single-node snapshot recovery into cluster deployments.

└──▷ GET THIS VERSION

$ git clone --branch v0.11.1 https://github.com/qdrant/qdrant.git
# already have the repo? check out this version:
$ git checkout v0.11.1

›Supports migrating collections from single-node deployments to cluster mode, including restoring single-node snapshots into a cluster deployment.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · November 25, 2022
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -396, November 25, 2022

deepset Haystack

NVIDIA Triton Inference Server

Zed

Milvus

Qdrant