| Name | langgate-transform JSON |
| Version |
0.3.0
JSON |
| download |
| home_page | None |
| Summary | Parameter transformation utilities for LangGate |
| upload_time | 2025-08-18 13:28:15 |
| maintainer | None |
| docs_url | None |
| author | Tanantor Ltd. |
| requires_python | >=3.13 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# LangGate Transform
Parameter transformation utilities for LangGate AI Gateway.
This package provides the core parameter transformation logic used by both:
- Local registry clients to transform parameters for direct model calls
- The Envoy external processor to transform parameters in the proxy
It implements a declarative approach to parameter transformation that can be:
1. Used directly in Python applications
2. Potentially reimplemented in other languages (like Go) for external processors
3. Extended with custom transformation rules
## Parameter Transformation Precedence
The transformation module follows a specific precedence order when applying parameter transformations:
### Defaults (applied only if key doesn't exist yet):
1. Model-specific defaults (highest precedence for defaults)
2. Pattern defaults (matching patterns applied in config order)
3. Service provider defaults
4. Global defaults (lowest precedence for defaults)
### Overrides/Removals/Renames (applied in order, later steps overwrite/modify earlier ones):
1. Input parameters (initial state)
2. Service-level API keys and base URLs
3. Service-level overrides, removals, renames
4. Pattern-level overrides, removals, renames (matching patterns applied in config order)
5. Model-specific overrides, removals, renames (highest precedence)
6. Model ID (always overwritten with service_model_id)
7. Environment variable substitution (applied last to all string values)
Raw data
{
"_id": null,
"home_page": null,
"name": "langgate-transform",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.13",
"maintainer_email": "Saran Connoly <saran@tanantor.com>",
"keywords": null,
"author": "Tanantor Ltd.",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/e7/76/8774f20842e36c8a1051581028bd95270e852a227c28d267efacb419be54/langgate_transform-0.3.0.tar.gz",
"platform": null,
"description": "# LangGate Transform\n\nParameter transformation utilities for LangGate AI Gateway.\n\nThis package provides the core parameter transformation logic used by both:\n- Local registry clients to transform parameters for direct model calls\n- The Envoy external processor to transform parameters in the proxy\n\nIt implements a declarative approach to parameter transformation that can be:\n1. Used directly in Python applications\n2. Potentially reimplemented in other languages (like Go) for external processors\n3. Extended with custom transformation rules\n\n## Parameter Transformation Precedence\n\nThe transformation module follows a specific precedence order when applying parameter transformations:\n\n### Defaults (applied only if key doesn't exist yet):\n1. Model-specific defaults (highest precedence for defaults)\n2. Pattern defaults (matching patterns applied in config order)\n3. Service provider defaults\n4. Global defaults (lowest precedence for defaults)\n\n### Overrides/Removals/Renames (applied in order, later steps overwrite/modify earlier ones):\n1. Input parameters (initial state)\n2. Service-level API keys and base URLs\n3. Service-level overrides, removals, renames\n4. Pattern-level overrides, removals, renames (matching patterns applied in config order)\n5. Model-specific overrides, removals, renames (highest precedence)\n6. Model ID (always overwritten with service_model_id)\n7. Environment variable substitution (applied last to all string values)\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Parameter transformation utilities for LangGate",
"version": "0.3.0",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "b9b5ed18157a1695cdd46b6c563fb4d084bf296a33ecd75943ff211062269752",
"md5": "25a2a41161ba7769b7c9621d2d43d21a",
"sha256": "4f721f89b653599168c37b739d6b703bacae99bb90ff4889e32e6cb6938b433c"
},
"downloads": -1,
"filename": "langgate_transform-0.3.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "25a2a41161ba7769b7c9621d2d43d21a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.13",
"size": 7135,
"upload_time": "2025-08-18T13:28:14",
"upload_time_iso_8601": "2025-08-18T13:28:14.017518Z",
"url": "https://files.pythonhosted.org/packages/b9/b5/ed18157a1695cdd46b6c563fb4d084bf296a33ecd75943ff211062269752/langgate_transform-0.3.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "e7768774f20842e36c8a1051581028bd95270e852a227c28d267efacb419be54",
"md5": "34035d9cd92e062c769809d4e9cde752",
"sha256": "4317edfa2862f9b21aef2284f32d52fd4654a1bedb8db0f0de86d523f9ce3087"
},
"downloads": -1,
"filename": "langgate_transform-0.3.0.tar.gz",
"has_sig": false,
"md5_digest": "34035d9cd92e062c769809d4e9cde752",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.13",
"size": 5400,
"upload_time": "2025-08-18T13:28:15",
"upload_time_iso_8601": "2025-08-18T13:28:15.057952Z",
"url": "https://files.pythonhosted.org/packages/e7/76/8774f20842e36c8a1051581028bd95270e852a227c28d267efacb419be54/langgate_transform-0.3.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-18 13:28:15",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "langgate-transform"
}
