Enable internal text embedding API #3441
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -770,6 +770,195 @@ | |
| "default": 4 | ||
| } | ||
| } | ||
| }, | ||
| "embeddings": { | ||
| "type": "object", | ||
| "description": "Configuration for text embedding/vectorization service. Supports OpenAI and Azure OpenAI providers.", | ||
| "additionalProperties": false, | ||
| "properties": { | ||
| "enabled": { | ||
| "type": "boolean", | ||
| "description": "Whether the embedding service is enabled. Defaults to true.", | ||
| "default": true | ||
| }, | ||
| "provider": { | ||
| "type": "string", | ||
| "description": "The embedding provider type.", | ||
| "enum": ["azure-openai", "openai"] | ||
| }, | ||
| "base-url": { | ||
| "type": "string", | ||
| "description": "The provider base URL. For Azure OpenAI, use the Azure resource endpoint. For OpenAI, use https://api.openai.com." | ||
| }, | ||
| "api-key": { | ||
| "type": "string", | ||
| "description": "The API key for authentication. Supports environment variable substitution with @env('VAR_NAME')." | ||
| }, | ||
| "model": { | ||
| "type": "string", | ||
| "description": "The model or deployment name. Required for Azure OpenAI (deployment name). For OpenAI, defaults to 'text-embedding-3-small' if not specified." | ||
| }, | ||
| "api-version": { | ||
| "type": "string", | ||
| "description": "Azure API version. Only used for Azure OpenAI provider.", | ||
| "default": "2023-05-15" | ||
| }, | ||
| "dimensions": { | ||
| "type": "integer", | ||
| "description": "Output vector dimensions. Defaults to 1536 if not specified. Useful for Redis schema alignment.", | ||
| "default": 1536, | ||
| "minimum": 1 | ||
| }, | ||
| "timeout-ms": { | ||
| "type": "integer", | ||
| "description": "Request timeout in milliseconds.", | ||
| "default": 30000, | ||
| "minimum": 1, | ||
| "maximum": 300000 | ||
| }, | ||
| "endpoint": { | ||
| "type": "object", | ||
| "description": "REST endpoint configuration for the embedding service.", | ||
| "additionalProperties": false, | ||
| "properties": { | ||
| "enabled": { | ||
| "type": "boolean", | ||
| "description": "Whether the /embed REST endpoint is enabled. Defaults to false.", | ||
| "default": false | ||
| }, | ||
| "path": { | ||
| "type": "string", | ||
| "description": "The URL path for the embedding endpoint. Defaults to '/embed'.", | ||
| "default": "/embed" | ||
| }, | ||
| "roles": { | ||
| "type": "array", | ||
| "description": "The roles allowed to access the embedding endpoint. Defaults to ['authenticated'].", | ||
| "default": ["authenticated"], | ||
| "items": { | ||
| "type": "string" | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| "health": { | ||
| "type": "object", | ||
| "description": "Health check configuration for the embedding service.", | ||
| "additionalProperties": false, | ||
| "properties": { | ||
| "enabled": { | ||
| "type": "boolean", | ||
| "description": "Whether health checks are enabled for embeddings. Defaults to false.", | ||
| "default": false | ||
| }, | ||
| "threshold-ms": { | ||
| "type": "integer", | ||
| "description": "The maximum response time in milliseconds to be considered healthy.", | ||
| "default": 1000, | ||
| "minimum": 1, | ||
| "maximum": 300000 | ||
| }, | ||
| "test-text": { | ||
| "type": "string", | ||
| "description": "The text to use for health check validation.", | ||
| "default": "health check" | ||
| }, | ||
| "expected-dimensions": { | ||
| "type": "integer", | ||
| "description": "The expected number of dimensions in the embedding result. If specified, dimension validation is performed.", | ||
| "minimum": 1 | ||
| } | ||
| } | ||
| }, | ||
| "cache": { | ||
| "type": "object", | ||
| "description": "Cache configuration for embedding results.", | ||
| "additionalProperties": false, | ||
| "properties": { | ||
| "enabled": { | ||
| "type": "boolean", | ||
| "description": "Whether caching is enabled for embeddings. Defaults to true.", | ||
| "default": true | ||
| }, | ||
| "level": { | ||
| "type": "string", | ||
| "description": "Cache level (L1 for in-memory only, L1L2 for in-memory + distributed). Defaults to L1.", | ||
| "enum": ["L1", "L1L2"], | ||
| "default": "L1" | ||
|
Collaborator
There was a problem hiding this comment. Shouldnt the default cache be
Author
There was a problem hiding this comment. In this phase we only support L1 via Fusion cache. In phase 2 we will enable support for L2 with redis which would default to L1 or L1L2 like you have suggested. |
||
| }, | ||
| "ttl-seconds": { | ||
| "type": "integer", | ||
| "description": "Time-to-live for cached embeddings in seconds. Defaults to 86400 (24 hours).", | ||
| "default": 86400, | ||
| "minimum": 1 | ||
| } | ||
| } | ||
| }, | ||
| "chunking": { | ||
| "type": "object", | ||
| "description": "Chunking configuration for text processing before embedding. Used to split large text inputs into smaller chunks.", | ||
| "additionalProperties": false, | ||
| "properties": { | ||
| "enabled": { | ||
| "type": "boolean", | ||
| "description": "Whether chunking is enabled. Defaults to true.", | ||
| "default": true | ||
| }, | ||
| "size-chars": { | ||
| "type": "integer", | ||
| "description": "The size of each chunk in characters.", | ||
| "default": 800, | ||
|
Collaborator
There was a problem hiding this comment. PR description says default is 1000. What is the correct default?
Author
There was a problem hiding this comment. Modified the PR description, you can refer to PRD as a SOT: #3331 |
||
| "minimum": 1 | ||
| }, | ||
| "overlap-chars": { | ||
| "type": "integer", | ||
| "description": "The number of characters to overlap between consecutive chunks. Overlap helps maintain context across chunk boundaries.", | ||
| "default": 100, | ||
| "minimum": 0 | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| "required": ["provider", "base-url", "api-key"], | ||
| "allOf": [ | ||
| { | ||
| "$comment": "Azure OpenAI requires the model (deployment name) to be specified.", | ||
| "if": { | ||
| "properties": { | ||
| "provider": { | ||
| "const": "azure-openai" | ||
| } | ||
| }, | ||
| "required": ["provider"] | ||
| }, | ||
| "then": { | ||
| "required": ["model"], | ||
| "properties": { | ||
| "api-version": { | ||
| "type": "string", | ||
| "description": "Azure API version. Required for Azure OpenAI provider.", | ||
| "default": "2023-05-15" | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| { | ||
| "$comment": "OpenAI does not require model (defaults to text-embedding-3-small) and does not use api-version.", | ||
| "if": { | ||
| "properties": { | ||
| "provider": { | ||
| "const": "openai" | ||
| } | ||
| }, | ||
| "required": ["provider"] | ||
| }, | ||
| "then": { | ||
| "properties": { | ||
| "api-version": false | ||
| } | ||
| } | ||
| } | ||
| ] | ||
| } | ||
| } | ||
| }, | ||
|
|
||
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.