Skip to main content

omop-llm

Shared chat/embedding backend contract for the OMOP stack, built on any-llm. One typed ModelBackend interface (sync and async methods, both real), a closed set of supported providers (local: ollama, llamacpp, vllm; cloud: openai, anthropic, gemini), and explicit capability declarations instead of provider-name guessing. Extended documentation can be found here.

from omop_llm import build_model_backend, Capabilities

backend = build_model_backend(
    provider="ollama", model="llama3:8b", base_url="http://localhost:11434",
    model_capabilities=Capabilities(),  # plain chat only -- nothing else needed here
)

# async
response = await backend.async_complete([{"role": "user", "content": "Hello"}])

# sync
response = backend.complete([{"role": "user", "content": "Hello"}])

Or resolved from an oa-configurator stack config:

from oa_configurator import Resolver, load_stack_config
from omop_llm import build_model_backend_from_resolved

resolved = Resolver(load_stack_config()).resolve_model("embed-default")
backend = build_model_backend_from_resolved(resolved)

See docs/index.md for the full design (provider registry, capability model, structured extraction).

Download files

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

Source Distribution

omop_llm-1.0.1.tar.gz (183.1 kB view details)

Uploaded Source

Built Distribution

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

omop_llm-1.0.1-py3-none-any.whl (25.9 kB view details)

Uploaded Python 3

File details

Details for the file omop_llm-1.0.1.tar.gz.

File metadata

  • Download URL: omop_llm-1.0.1.tar.gz
  • Upload date:
  • Size: 183.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for omop_llm-1.0.1.tar.gz
Algorithm Hash digest
SHA256 cebdb7df66759f516198477c97e882534d8700787b0bae001b43a8f8071be964
MD5 c2f008ace40e8e1623a97c3232b72df6
BLAKE2b-256 f2aedec515aac6273c562b2edd2bea0b996d40a65092213907e2eeb09098fc46

See more details on using hashes here.

Provenance

The following attestation bundles were made for omop_llm-1.0.1.tar.gz:

Publisher: publish.yml on AustralianCancerDataNetwork/omop-llm

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

File details

Details for the file omop_llm-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: omop_llm-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 25.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for omop_llm-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 aecfa1578286c3fad8f61c33032bd63355f8079ee5915ad2941a87e87cd3796a
MD5 6c44cb3e0c422b215dca3394cac28312
BLAKE2b-256 1e14fc6782952879b08d02bd64c5b7fd1114465d826196681fd69a69e8207db0

See more details on using hashes here.

Provenance

The following attestation bundles were made for omop_llm-1.0.1-py3-none-any.whl:

Publisher: publish.yml on AustralianCancerDataNetwork/omop-llm

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

Release history Release notifications | RSS feed

This release

1.0.1 This release

2 files

0.1.1

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page