Skip to main content

Cost-shield foundation for AI workloads: OpenAI + Anthropic Batch APIs, live/batch urgency router, shared embedding cache.

Project description

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 routerBatchRouter.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.

Project details


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-0.1.1.tar.gz (22.4 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-0.1.1-py3-none-any.whl (17.4 kB view details)

Uploaded Python 3

File details

Details for the file matrx_batch-0.1.1.tar.gz.

File metadata

  • Download URL: matrx_batch-0.1.1.tar.gz
  • Upload date:
  • Size: 22.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for matrx_batch-0.1.1.tar.gz
Algorithm Hash digest
SHA256 a40dae11eee4959ae993b9cab77d00e3e964a704c06767160eb93a18150578d6
MD5 908d47b8267a92b140d5844067d32b96
BLAKE2b-256 e44ce7cf13a36a7793d59ecc9d5984d8ada598b2f472a53e7fd7731c07bfff14

See more details on using hashes here.

Provenance

The following attestation bundles were made for matrx_batch-0.1.1.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-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: matrx_batch-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 17.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for matrx_batch-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 26abecbef65a7a3fcefbe8ca94384249783daf0642f4eb2557e633b6785dcf85
MD5 9387c7f367d9a7050faa39f9a20ea132
BLAKE2b-256 f2efd1b8dc37695caf433d03569d733f98f494a601cad288493741ce6657dc11

See more details on using hashes here.

Provenance

The following attestation bundles were made for matrx_batch-0.1.1-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 Pingdom Monitoring Sentry Error logging StatusPage Status page