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 (0.2.14)

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-0.2.10.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-0.2.10-py3-none-any.whl (43.0 kB view details)

Uploaded Python 3

File details

Details for the file matrx_batch-0.2.10.tar.gz.

File metadata

  • Download URL: matrx_batch-0.2.10.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-0.2.10.tar.gz
Algorithm Hash digest
SHA256 7281e7f7b816052e8e2f39072084078e048de9345bbd4cdc7e77d007c91c3455
MD5 5b8b61b22fd53b607ffacb7f90a665f3
BLAKE2b-256 0ee024f9605d3a3a1834b99bcf6217ebe3c858b0a12b9b208c2fed0451ebd642

See more details on using hashes here.

Provenance

The following attestation bundles were made for matrx_batch-0.2.10.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-0.2.10-py3-none-any.whl.

File metadata

  • Download URL: matrx_batch-0.2.10-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-0.2.10-py3-none-any.whl
Algorithm Hash digest
SHA256 92f4cb28b000dc84c2aea7ceda6aa655bb9b34299943fa92847779cc9d424ddc
MD5 07a16d41aa3f2e6592cb1b6225fd3a96
BLAKE2b-256 4d09e65d33d53ae51031f824b9ef5b26ddaa23697ae671eba6bcd86eecad0fa9

See more details on using hashes here.

Provenance

The following attestation bundles were made for matrx_batch-0.2.10-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