matrx-batch

Cost-shield foundation for AI workloads in the Matrx ecosystem.

Three primitives:

  1. OpenAI Batch API + Anthropic Message Batches — submit JSONL, poll status, fetch results. Async wrappers over the provider SDKs.
  2. Urgency router — BatchRouter.submit(job) routes a job to live inference, to the provider's Batch API (50% discount, 24h SLA), or makes a cost-based decision automatically.
  3. Embedding cache — content-addressable (SHA256 of model || text) reuse of embedding vectors across the org. Backed by rag.embedding_cache via a host-supplied asyncpg pool.

Dependency posture

matrx-batch sits one notch above matrx-utils in the dependency graph and is consumed by matrx-rag (embedding cache) and matrx-ai (urgency router, future). It MUST NOT import from aidream/ or from any other matrx-* sibling — every cross-boundary dependency comes in via matrx_batch.configure(...).

Usage (host-side wiring)

import matrx_batch
from openai import AsyncOpenAI
from anthropic import AsyncAnthropic

matrx_batch.configure(
    openai_client=AsyncOpenAI(api_key=settings.OPENAI_API_KEY),
    anthropic_client=AsyncAnthropic(api_key=settings.ANTHROPIC_API_KEY),
    pool_factory=lambda: get_async_pg_pool(),
    cost_check=_aidream_budget_precheck,
)

# Wire the cache into matrx-rag's embed() funnel
import matrx_rag
matrx_rag.configure(embedding_cache=matrx_batch.get_embedding_cache())

Usage (consumer)

from matrx_batch import BatchRouter, BatchableJob

router = BatchRouter()
receipt = await router.submit(
    BatchableJob(
        kind="chat",
        provider="anthropic",
        urgency="auto",
        payload={"model": "claude-haiku-4-5", "messages": [...]},
        estimated_tokens_in=8200,
    )
)

See also

  • CLAUDE.md — package rules and injection-point contract.
  • matrx_batch/embedding_cache.py — chunk-level embedding reuse.
  • matrx_batch/router.py — urgency routing decisions.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.2.19)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for armanisadeghi from gravatar.com armanisadeghi

Credits

Author: Matrx

License

MIT License (MIT)

Requires

Python >=3.13

Provides Extra

dev

Tags

anthropic batch cost embeddings matrx openai

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

matrx_batch-0.2.18.tar.gz (44.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

matrx_batch-0.2.18-py3-none-any.whl (43.0 kB view details)

Uploaded Python 3

File details

Details for the file matrx_batch-0.2.18.tar.gz.

File metadata

  • Download URL: matrx_batch-0.2.18.tar.gz
  • Upload date:
  • Size: 44.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for matrx_batch-0.2.18.tar.gz
Algorithm Hash digest
SHA256 f34c25a9ee022c16f69fed0fe92a71217402e01faea0481ed62c6c0c0751eae6
MD5 9d908c0d976bfd4e686d7346af20eea1
BLAKE2b-256 04ed5649105cb4f20f62019d85b9f8ef998c154886a6e3d159131e8f97bb37ca

See more details on using hashes here.

Provenance

The following attestation bundles were made for matrx_batch-0.2.18.tar.gz:

Publisher: publish-package.yml on AI-Matrix-Engine/aidream

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file matrx_batch-0.2.18-py3-none-any.whl.

File metadata

  • Download URL: matrx_batch-0.2.18-py3-none-any.whl
  • Upload date:
  • Size: 43.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for matrx_batch-0.2.18-py3-none-any.whl
Algorithm Hash digest
SHA256 7e68fbfdd74ea18677126430c63beb1edd8ccb50156981e1df5f0ba1eb244ae7
MD5 6fdb188b5b8980be5a11da28d96c5051
BLAKE2b-256 14427e835f514c86b4a5914a7ec479a776835382b1705e6283a2563345abeea2

See more details on using hashes here.

Provenance

The following attestation bundles were made for matrx_batch-0.2.18-py3-none-any.whl:

Publisher: publish-package.yml on AI-Matrix-Engine/aidream

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page