The AI Toolchain — issue -400, July 30, 2022

Haystack v1.6.0 adds audio QA nodes, multi-hop dense retrieval, in-memory knowledge graphs, and remote model saving to HuggingFace Hub.

$ git clone --branch v1.6.0 https://github.com/deepset-ai/haystack.git
# already have the repo? check out this version:
$ git checkout v1.6.0

from haystack.nodes import FARMReader

reader = FARMReader(model_name_or_path="roberta-base")
reader.train(data_dir="my_squad_data", train_filename="squad2.json", n_epochs=1, save_dir="my_model")
reader.save_to_remote(repo_id="your-user-name/roberta-base-squad2", private=True, commit_message="First version of my qa model trained with Haystack")

from haystack.nodes import MultihopEmbeddingRetriever
from haystack.document_stores import InMemoryDocumentStore

document_store = InMemoryDocumentStore()
retriever = MultihopEmbeddingRetriever(
    document_store=document_store,
    embedding_model="deutschmann/mdr_roberta_q_encoder",
)

from pathlib import Path
from haystack.nodes import Text2SparqlRetriever
from haystack.document_stores import InMemoryKnowledgeGraph

kg = InMemoryKnowledgeGraph(index="tutorial10")
kg.create_index()
kg.import_from_ttl_file(index="tutorial10", path=Path("data/tutorial10/triples.ttl"))

kgqa_retriever = Text2SparqlRetriever(knowledge_graph=kg, model_name_or_path=Path("../saved_models/tutorial10/hp_v3.4"))
print(kgqa_retriever.retrieve(query="In which house is Harry Potter?"))

• ›Adds DocumentToSpeech node for indexing pipelines that generates an audio file per document and stores it in a SpeechDocument alongside text content (GPU recommended for indexing speed).
• ›Adds AnswerToSpeech node for QA pipelines to generate audio of an answer on the fly from SpeechDocuments.
• ›Adds save_to_remote(repo_id, private, commit_message) method to FARMReader for uploading trained models directly to the Hugging Face Model Hub; supports private=True and auth via use_auth_token=True on reload.
• ›Adds MultihopEmbeddingRetriever node that applies iterative multi-hop dense retrieval with a shared encoder for query and documents, suited for complex open-domain questions requiring multiple document hops.
• ›Adds InMemoryKnowledgeGraph document store for storing and querying knowledge graphs without a dedicated graph database, supporting create_index() and import_from_ttl_file() for loading triples from .ttl files.

ONNX Runtime v1.12 adds SNPE EP, XNNPACK EP preview, opset 17, BeamSearch op, and FusedAdam optimizer for training.

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

• ›New enable_dynamic_shapes runtime configuration option for the OpenVINO EP to enable dynamic shapes per inference iteration.
• ›Adds new BeamSearch operator for encoder-decoder transformer models.
• ›Supports invoking individual ops without creating a separate graph, enabling custom op development to reuse ORT code.
• ›Supports feeding external initializers (for large models) as byte arrays for model inferencing.
• ›New SNPE Execution Provider (production release).

Triton v2.24.0 enables auto-complete by default, adds asyncio Python APIs, a C++ BLS example, and a concurrent model-load thread pool.

$ git clone --branch v2.24.0 https://github.com/triton-inference-server/server.git
# already have the repo? check out this version:
$ git checkout v2.24.0

$ tritonserver --model-repository=/models --disable-auto-complete-config

$ tritonserver --model-repository=/models --model-load-thread-count=8

• ›Replaces the soft-deprecated --strict-model-config option with the new --disable-auto-complete-config CLI option, and enables Auto-Complete model configuration by default.
• ›Adds --model-load-thread-count tritonserver CLI option to configure the size of a new thread pool for concurrently loading models, reducing service downtime.
• ›Adds a new asyncio-compatible API (beta) to the Python gRPC/HTTP client libraries.
• ›Supports init_ops parameters for TensorFlow TF1.x GraphDef models, configurable via JSON file.
• ›New example backend demonstrating Business Logic Scripting (BLS) in C++.

Zed v0.49.0 adds IME text input support, diagnostic hover messages, and middle-click tab close.

$ git clone --branch v0.49.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.49.0

• ›Adds full macOS IME text input integration, including the character palette, dead keys, and the IME candidate window.
• ›Adds the ability to hover over a diagnostic with the mouse to view the full error message inline.
• ›Adds middle-mouse-button click to close editor tabs.

$ git clone --branch v0.48.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.48.0

$ git clone --branch v0.47.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.47.0

$ git clone --branch v0.46.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.46.0

{
  "format_on_save": {
    "external": {
      "command": "prettier",
      "arguments": ["--stdin-filepath", "{buffer_path}"]
    }
  }
}

{
  "format_on_save": "off"
}

$ git clone --branch v0.44.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.44.0

$ git clone --branch v0.43.0 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.43.0

{
  "autosave": {
    "after_delay": {
      "milliseconds": 1000
    }
  }
}

Milvus 2.1.0 adds VARCHAR type, in-memory replicas, embedded install, Kafka support, RESTful API, and TLS/auth security.

$ git clone --branch v2.1.0 https://github.com/milvus-io/milvus.git
# already have the repo? check out this version:
$ git checkout v2.1.0

• ›Adds VARCHAR scalar data type with MARISA-trie-based inverted index for prefix query and exact match, usable as an output field or for attribute filtering.
• ›Adds in-memory replicas, enabling data to be loaded across multiple query nodes to scale read throughput without changing the dataset.
• ›Adds RESTful API (Beta) for Milvus, built on the GIN web framework, enabling PHP and Ruby applications to interact with Milvus over HTTP.
• ›Adds Apache Kafka support (Beta) as a message storage backend, configurable via Milvus configuration.
• ›Adds username, password, and TLS connection support, plus secure connections to S3, Kafka, and etcd dependencies.

Qdrant v0.8.5 adds full-storage snapshots, parallel segment loading, and a shard distribution API.

$ git clone --branch v0.8.5 https://github.com/qdrant/qdrant.git
# already have the repo? check out this version:
$ git checkout v0.8.5

• ›Adds a full storage snapshot endpoint that captures all collections and aliases in a single API call.
• ›New API for viewing the shard distribution of a collection across a distributed deployment.
• ›Automatic selection of the number of shards when creating a collection in a distributed deployment.
• ›Propagates the wait flag during distributed calls for consistent write-acknowledgement behavior.
• ›More even point distribution across shards in distributed deployments.

$ git clone --branch v0.8.4 https://github.com/qdrant/qdrant.git
# already have the repo? check out this version:
$ git checkout v0.8.4

Weaviate v1.14.0 adds Prometheus monitoring, official multi-distance-metric support, and class-namespaced REST endpoints.

$ git clone --branch v1.14.0 https://github.com/weaviate/weaviate.git
# already have the repo? check out this version:
$ git checkout v1.14.0

$ curl -X POST 'http://localhost:8080/v1/schema' \
  -H 'Content-Type: application/json' \
  -d '{"class": "MyClass", "vectorIndexConfig": {"distance": "l2-squared"}}'

• ›Adds new REST endpoints that include the class name as a namespace — e.g. object operations scoped to a specific class — eliminating ambiguity when an ID exists in multiple classes; old ID-only endpoints remain but are deprecated and will be removed in a future version.
• ›Officially supports cosine, l2-squared, and dot distance metrics in the vector index, replacing the previous experimental-only status for non-cosine metrics.
• ›Introduces distance as the supported similarity field in the API, replacing certainty (now deprecated) wherever it appears in queries.
• ›Adds Prometheus-compatible monitoring for import metrics, HNSW operations (inserts, deletes, cleanup), LSM store segment and compaction details, startup and crash-recovery metrics, batch-delete operations, and total imported object counts.
• ›Adds support for aggregating date fields in aggregate queries.