dbx-tools-model

Python contracts and runtime helpers for Databricks Model Serving. This package mirrors the reusable parts of @dbx-tools/shared-model and @dbx-tools/model without AppKit cache or Mastra dependencies.

Install from PyPI:

pip install dbx-tools-model

To install the current main branch directly from the repository instead:

pip install "dbx-tools-model @ git+https://github.com/reggie-db/dbx-tools.git@main#subdirectory=packages/py/model"

Key features:

  • stable Pydantic endpoint, profile, query, and ranked-result models;
  • live endpoint listing through a structural WorkspaceClient protocol;
  • canonical first-party service model names exposed through a typed serviceNames map on library endpoint results;
  • score-driven model classification with family fallbacks;
  • reasoning-effort levels inferred from Databricks served-entity identity, with endpoint-family fallback for summaries that omit it;
  • flexible family, version, and model parsing shared by classification, reasoning, sorting, and downstream integrations;
  • exact and fuzzy endpoint resolution with deterministic class ordering;
  • Databricks invocation URL and process-serialized per-request authentication helpers, so concurrent SDK refreshes converge;
  • shared Responses-only endpoint policy, including Codex and GPT 5.4+ while excluding GPT-OSS;
  • OpenAI chat request sanitization, assistant-prefill repair, and content extraction;
  • embedding vector extraction with optional dimension validation.
from databricks.sdk import WorkspaceClient
from dbx_tools.model import ModelClass, list_serving_endpoints, resolve_model

endpoints = list_serving_endpoints(WorkspaceClient())
selection = resolve_model(endpoints, model_class=ModelClass.CHAT_BALANCED)
print(selection.model_id)
print(endpoints[0].service_names)
print(
    next(
        endpoint.reasoning_efforts for endpoint in endpoints if endpoint.name == selection.model_id
    )
)

The Python port intentionally omits AppKit CacheManager integration, Mastra-specific adapters, and browser-only schemas. Callers can cache the plain Pydantic results with their preferred Python cache.

Model-name parsing produces provider-neutral components without maintaining a second family registry:

from dbx_tools.model.models import parse_model_name

parsed = parse_model_name("databricks-qwen35-122b-a10b")
assert parsed is not None
assert parsed.family == "qwen"
assert parsed.version == (3, 5)

Known first-party identities are keyed by ModelService, such as openai, anthropic, google, xai, deepseek, moonshot, alibaba, zhipu, and meta. A model without a canonical name on one of those services has no entry; the package does not invent names for third-party hosts.

Relationship to the Databricks SDK

Use the native SDK directly when an endpoint name is already known and its typed query method fits the request. Use this package when endpoint choice, stable cross-runtime models, OpenAI-shaped HTTP invocation, or provider-neutral chat and embedding normalization is the repetitive part.

Module map

  • models — Pydantic wire contracts plus shared family/version/model parsing;
  • reasoning — model-family and served-entity reasoning-level inference;
  • classify, classes, fallback — model taxonomy and ordering;
  • resolve — exact/fuzzy ranking and single-model selection;
  • serving — structural WorkspaceClient endpoint listing;
  • invoke - URLs, Responses-only policy, process-serialized SDK authentication headers, and JSON POST helpers;
  • chat, embedding — request repair/sanitization and response extraction.

Project links

Data verified by PyPI on Sep 5, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.6.186)

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for reggie-db from gravatar.com reggie-db

GitHub Statistics

Data verified by PyPI on Sep 5, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

Requires

Python <3.14, >=3.10

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

dbx_tools_model-0.6.170.tar.gz (14.1 kB view details)

Uploaded Source

Built Distribution

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

dbx_tools_model-0.6.170-py3-none-any.whl (19.0 kB view details)

Uploaded Python 3

File details

Details for the file dbx_tools_model-0.6.170.tar.gz.

File metadata

  • Download URL: dbx_tools_model-0.6.170.tar.gz
  • Upload date:
  • Size: 14.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for dbx_tools_model-0.6.170.tar.gz
Algorithm Hash digest
SHA256 ea11adad2999dd4b9497a54e2167ee716d659a2dc56a3beaf4f8d968758a327a
MD5 a03abdd45d3c3e3966f3903d6f0a1feb
BLAKE2b-256 4e373955511682d12968c936e096112e3431fb176a8e560ad26dacb52ac1c17c

See more details on using hashes here.

Provenance

The following attestation bundles were made for dbx_tools_model-0.6.170.tar.gz:

Publisher: python-release.yml on reggie-db/dbx-tools

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

File details

Details for the file dbx_tools_model-0.6.170-py3-none-any.whl.

File metadata

File hashes

Hashes for dbx_tools_model-0.6.170-py3-none-any.whl
Algorithm Hash digest
SHA256 de0b49b8cef26c72a37b4eee9567fba6c88f16380f746a6ff098744b4842a54a
MD5 5af90fcb32918546bb0dd4e5a3ba1ddf
BLAKE2b-256 de35bbee9021b45a3a1c87c004523b8e20db2cbed1902525fcd60397e9b09421

See more details on using hashes here.

Provenance

The following attestation bundles were made for dbx_tools_model-0.6.170-py3-none-any.whl:

Publisher: python-release.yml on reggie-db/dbx-tools

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

Release history Release notifications | RSS feed

0.6.186

2 files

0.6.185

2 files

0.6.183

2 files

0.6.182

2 files

0.6.181

2 files

0.6.180

2 files

0.6.179

2 files

0.6.177

2 files

0.6.176

2 files

0.6.175

2 files

0.6.174

2 files

0.6.173

2 files

0.6.172

2 files

0.6.171

2 files

This release

0.6.170 This release

2 files

0.6.168

2 files

0.6.163

2 files

0.6.161

2 files

0.6.160

2 files

0.6.158

2 files

0.6.153

2 files

0.6.147

2 files

0.6.146

2 files

0.6.145

2 files

0.6.144

2 files

0.6.143

2 files

0.6.142

2 files

0.6.141

2 files

0.6.140

2 files

0.6.139

2 files

0.6.138

2 files

0.6.137

2 files

0.6.136

2 files

0.6.135

2 files

0.6.134

2 files

0.6.133

2 files

0.6.131

2 files

0.6.130

2 files

0.6.129

2 files

0.6.128

2 files

0.6.127

2 files

0.6.126

2 files

0.6.125

2 files

0.6.124

2 files

0.6.123

2 files

0.6.122

2 files

0.6.121

2 files

0.6.120

2 files

0.6.119

2 files

0.6.118

2 files

0.6.117

2 files

0.6.116

2 files

0.6.115

2 files

0.6.114

2 files

0.6.113

2 files

0.6.112

2 files

0.6.111

2 files

0.6.110

2 files

0.6.109

2 files

0.6.108

2 files

0.6.107

2 files

0.6.106

2 files

0.6.105

2 files

0.6.104

2 files

0.6.103

2 files

0.6.102

2 files

0.6.101

2 files

0.6.100

2 files

0.6.99

2 files

0.6.98

2 files

0.6.97

2 files

0.6.96

2 files

0.6.95

2 files

0.6.94

2 files

0.6.93

2 files

0.6.92

2 files

0.6.91

2 files

0.6.90

2 files

0.6.89

2 files

0.6.88

2 files

0.6.87

2 files

0.6.86

2 files

0.6.85

2 files

0.6.82

2 files

0.6.78

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