Backfill issue -397 — 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   # 6 tools matched

AI & LLM Tooling

◆ AI Agent Frameworks

deepset Haystack

v1.10.0 NOTES

Haystack v1.10 adds OpenAI embeddings, multimodal retrieval, HNSW/OpenSearch support, and multi-platform Docker images.

└──▷ GET THIS VERSION

$ git clone --branch v1.10.0 https://github.com/deepset-ai/haystack.git
# already have the repo? check out this version:
$ git checkout v1.10.0

└──▷ USE IT

Perform text-to-image retrieval using a multimodal CLIP model across an image document store.

python

retriever = MultiModalRetriever(
    document_store=InMemoryDocumentStore(embedding_dim=512),
    query_embedding_model="sentence-transformers/clip-ViT-B-32",
    query_type="text",
    document_embedding_models={"image": "sentence-transformers/clip-ViT-B-32"}
)

›Adds OpenAIEmbeddingEncoder to EmbeddingRetriever, enabling document and query embeddings via OpenAI models ada, babbage, davinci, or curie using an API key.
›Adds MultiModalRetriever supporting independent modalities for query and documents — enabling text-to-image, text-to-table, text-to-text, image similarity, and table similarity retrieval via configurable query_embedding_model, query_type, and document_embedding_models parameters.
›Adds filters parameter to MostSimilarDocumentsPipeline.run() and run_batch() for filtered similarity searches.
›Adds HNSW support for cosine similarity in FAISS-backed OpenSearch (FAISSDocumentStore with OpenSearch).
›Adds support for Elasticsearch 7.16.2 in ElasticSearchDocumentStore.

+3 moreshow less

›Adds exponential backoff decorator applied to OpenAI requests to handle rate limiting.
›Updates EntityExtractor to handle long texts with improved postprocessing.
›Publishes deepset/haystack Docker images for both linux/amd64 and linux/arm64 platforms.

└──▷ BREAKING ON UPGRADE

!The text argument in the embed_queries method for DensePassageRetriever and EmbeddingRetriever is renamed to queries; callers using the keyword argument text= will break.

Was this useful?

◆ AI Model & Data Infrastructure

Microsoft ONNX Runtime

v1.13.1 NOTES

ONNX Runtime v1.13.1 adds CANN EP, new quantization APIs, XNNPACK threadpool support, and 4 GB WebAssembly memory.

└──▷ GET THIS VERSION

$ git clone --branch v1.13.1 https://github.com/microsoft/onnxruntime.git
# already have the repo? check out this version:
$ git checkout v1.13.1

└──▷ USE IT

Reduce peak memory on mobile by having the runtime read initializers directly from the ORT model byte buffer instead of copying them.

python

session_options.add_session_config_entry('session.use_ort_model_bytes_directly', '1')
session_options.add_session_config_entry('session.use_ort_model_bytes_for_initializers', '1')
session = onnxruntime.InferenceSession('model.ort', sess_options=session_options)

›Sets session.use_ort_model_bytes_directly and session.use_ort_model_bytes_for_initializers to 1 in SessionOptions config to load ORT format model initializers directly from bytes, reducing peak memory usage on mobile.
›Adds new QuantConfig-based quantize API for general quantization workflows.
›Exposes all arena configs in the Python API in an extensible way.
›Adds new quantized operators: SoftMax, Split, and Where.
›Adds a quantization debugging tool to identify sensitive nodes/layers from accuracy-drop discrepancies.

+15 moreshow less

›New CANN Execution Provider (CANN EP) contributed by Huawei for initial support of Ascend 310 hardware.
›TensorRT EP adds a build option to link against a pre-built onnx-tensorrt parser, enabling no-code TensorRT minor version upgrades and support for TensorRT 8.5 EA.
›TensorRT EP adds uint8 data type support.
›OpenVINO EP adds support for INT8 QDQ models from NNCF, Intel 13th Gen Core (Raptor Lake), and preview support for Intel Data Center GPU Flex Series and Intel Arc GPU.
›DirectML EP adds new ops: LayerNormalization, Gelu, MatMulScale, DFT, and FusedMatMul (contrib).
›SNPE EP NuGet package (Microsoft.ML.OnnxRuntime.Snpe) is now available and adds support for Windows Dev Kit 2023.
›XNNPACK EP adds QDQ format model support with new kernels: AveragePool, Softmax, QLinearConv, QLinearAveragePool, and QLinearSoftmax.
›XNNPACK EP adds threadpool support for configurable parallelism.
›WebAssembly build now supports up to 4 GB memory.
›Web build adds initial XNNPACK support for Wasm optimizations.
›Web build adds source build support for onnxruntime-extensions and sentencepiece.
›Adds fused attention CUDA kernels for BERT, fusing Add (bias) and Transpose of Q/K/V into one kernel for Attention and LongformerAttention.
›Reduces GEMM computation in LongformerAttention via a new weight format.
›Official ONNX Runtime GPU packages are now built with CUDA 11.6.
›Training packages updated to CUDA 11.6 with Aten support added for GroupNorm, InstanceNormalization, and Upsample nearest.

└──▷ BREAKING ON UPGRADE

!ORT format models must be regenerated: the mobile EP kernel format changed from hashes to operator constraint information and is NOT backwards compatible.
!Official ONNX Runtime GPU packages now require CUDA version >=11.6 (previously 11.4).
!NUPHAR EP code has been removed.
!Building ORT from source now requires a C++17 compiler; on Linux, GCC >=7.0 is required.
!Minimal numpy version for ONNX Runtime Python packages is now 1.21.6 (raised from 1.21.0).
!Windows 8.x is no longer supported in NuGet/C API prebuilt binaries (source builds retain Windows 7+ support).
!CUDA 10.x support removed at the source code level.
!Training packages drop CUDA 10.2 and 11.3 support.

Was this useful?

NVIDIA Triton Inference Server

v2.26.0 NOTES

Triton v2.26.0 adds CPU metrics, dynamic logging config, GPU metrics in Perf Analyzer, and a quick-search mode for Model Analyzer.

└──▷ GET THIS VERSION

$ git clone --branch v2.26.0 https://github.com/triton-inference-server/server.git
# already have the repo? check out this version:
$ git checkout v2.26.0

›Adds CPU metrics reporting to Triton's Prometheus metrics endpoint.
›Adds a logging protocol extension enabling users to change logging configuration dynamically at runtime.
›Adds --disable-auto-complete-config launch flag awareness note: users can specify custom TensorRT plugins via command-line option in addition to LD_PRELOAD.
›Adds GPU metrics gathering to Perf Analyzer, improving accuracy of metrics also consumed by Model Analyzer.
›Adds a 'quick search' algorithm to Model Analyzer to drastically reduce model configuration search time.

+3 moreshow less

›Adds a developer tools GitHub repository providing a simplified interface to the Triton Core shared library (beta).
›Enables auto-completion of model configuration for the OpenVINO backend.
›Enables the Python backend to emit log messages through Triton's native logger.

Was this useful?

◆ AI Coding Agents

Zed

v0.61.0 3 RELEASES · 2022-10-13 → 2022-10-18 NOTES STABLE

Zed v0.61.0 adds page-cursor key bindings and journal file location settings.

└──▷ GET THIS VERSION

$ git clone --branch v0.61.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.61.0

›Adds key bindings shift-pageup and shift-pagedown to move the cursor up and down by a full page, and ctrl-v/alt-v to scroll by one page and center the cursor.
›Adds settings to customize the locations and names of journal files.
›Enhances breadcrumbs to display the complete file path for files external to the project that are opened via a language server request.

2 more releases in this issue · 2022-10-13 → 2022-10-18

v0.60.0 NOTES STABLE

Zed v0.60.0 redesigns collaboration around calls, adds vertical scrollbars, and expands Vim mode text objects.

└──▷ GET THIS VERSION

$ git clone --branch v0.60.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.60.0

›Redesigns collaboration workflow around *calls*: open the collaboration menu with cmd+shift+c or the + button in the title bar to call contacts, share projects, and add participants — replacing the old 'request to join' model.
›Adds vertical scrollbars to editors.
›Adds sentence and word text objects in Vim mode.
›Implements page up and page down navigation.
›Enhances the theme selector to persist the chosen theme to the settings file.

v0.59.0 NOTES STABLE

Zed v0.59.0 adds git diff gutter markers and HTML language support.

└──▷ GET THIS VERSION

$ git clone --branch v0.59.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.59.0

›Adds git diff markers to the editor gutter, visually indicating changed lines alongside open files.
›Adds HTML language support.

Was this useful?

Other / Uncategorized

◆ VECTOR DB RAG

Qdrant

v0.11.0 NOTES

Qdrant v0.11.0 adds replication for HA distributed deployments, a write-disable admin API, and an exact search parameter.

└──▷ GET THIS VERSION

$ git clone --branch v0.11.0 https://github.com/qdrant/qdrant.git
# already have the repo? check out this version:
$ git checkout v0.11.0

└──▷ TRY IT

Validate HNSW index accuracy by running an exact nearest-neighbor search against the same query and comparing results.

$ POST /collections/{collection_name}/points/search
{
  "vector": [0.1, 0.2, 0.3],
  "limit": 10,
  "params": {
    "exact": true
  }
}

›Adds exact search parameter to force exact vector search even when an HNSW ANN index is built, enabling accuracy validation of index configurations.
›New administration API allows disabling write operations to the service when search availability must be prioritized over updates (e.g., when a memory usage watermark is reached).
›Replication support enables high-availability distributed deployments, combining with sharding to scale collection size and cluster throughput while eliminating single points of failure.
›Info API now reports indexed payload point counts, allowing verification that payload values are correctly formatted for indexing.

└──▷ BREAKING ON UPGRADE

!Distributed deployment in v0.11.0 is incompatible with previous versions due to changes required for replica set implementation; existing distributed clusters cannot be upgraded in place.

Was this useful?

Weaviate

v1.16.0 2 RELEASES · 2022-10-11 → 2022-10-31 NOTES STABLE

Weaviate v1.16 adds distributed multi-node backups, null/length property filtering, ref2vec-centroid, Cohere and HuggingFace text2vec modules, and a cluster nodes status API.

└──▷ GET THIS VERSION

$ git clone --branch v1.16.0 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout v1.16.0

›Adds the ref2vec-centroid module, enabling vectorization of objects based on the centroid of their referenced objects' vectors.
›Adds the text2vec-cohere module for Cohere-powered text vectorization, including support for the experimental multilingual-2210-alpha Cohere model.
›Adds the text2vec-huggingface module with support for the HuggingFace Inference API.
›Adds an API endpoint to view cluster node status, surfacing per-node health and shard information.
›Adds support for OpenID scopes configuration, allowing operators to specify required scopes for OIDC authentication.

+7 moreshow less

›Adds a default vector distance metric setting, letting operators define the cluster-wide default metric for new classes.
›Extends one-command backups (introduced in v1.15) to distributed multi-node setups; backups from v1.15 single-node setups remain backward-compatible.
›Adds null-state property indexing and filtering, enabling efficient queries to find objects where a given property is set or unset — must be activated before importing data.
›Adds property-length indexing and filtering, enabling efficient queries to filter objects by the length of a property value — must be activated before importing data.
›Marks all shards as read-only automatically when a configurable memory threshold is reached, preventing data corruption under memory pressure.
›Allows creating class schemas with self-referential (recursive) references.
›Updates the OpenAI text2vec module to use the current OpenAI embeddings API.

1 more release in this issue · 2022-10-11 → 2022-10-31

v1.15.4 NOTES STABLE

Weaviate v1.15.4 adds support for all AWS IAM-based authorizations.

└──▷ GET THIS VERSION

$ git clone --branch v1.15.4 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout v1.15.4

›Adds support for all AWS IAM-based authorization methods.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · October 31, 2022
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -397, October 31, 2022

deepset Haystack

Microsoft ONNX Runtime

NVIDIA Triton Inference Server

Zed

Qdrant

Weaviate