-
Notifications
You must be signed in to change notification settings - Fork 304
Add internal text embedding system #3113
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
robertopc1
wants to merge
18
commits into
Azure:main
Choose a base branch
from
robertopc1:add-internal-text-embedding-system
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+3,817
−122
Open
Changes from all commits
Commits
Show all changes
18 commits
Select commit
Hold shift + click to select a range
0dc589e
Initial plan
Copilot d3187bd
Add EmbeddingsOptions and EmbeddingProviderType configuration models
Copilot 6064826
Add CLI configure options for embeddings and register embedding service
Copilot 0653f15
Add unit tests for embeddings and update JSON schema with embeddings …
Copilot 21e81b9
Simplify HttpClient registration for embedding service
Copilot 0cd8e53
Plan for embedding service enhancements
Copilot 7fa1c49
Refactor embedding code into dedicated namespaces
Copilot c3f6937
Fix property renames and update tests
Copilot 1e18c25
Add EmbeddingsOptionsConverter and fix all tests
Copilot 857203a
Address code review feedback
Copilot 89cb2d9
Address PR feedback: Add Azure OpenAI validation, cache key security,…
Copilot 64b592e
Optimize ProviderName to avoid repeated string allocations
Copilot e8d7238
Fix schema mismatch, remove unused field, add enabled handling, valid…
Copilot d9c8a29
Add embedding health check execution and update JSON schema with endp…
Copilot 3e02c0f
Add EmbeddingController for /embed REST endpoint with role-based auth…
Copilot 5c05464
Address code review feedback for EmbeddingController
Copilot c9eba20
fix: manually deserialize EmbeddingsEndpointOptions and EmbeddingsHea…
robertopc1 d3a5209
feat: add embeddings config validation and unit tests
robertopc1 File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
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
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
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 |
|---|---|---|
|
|
@@ -8,6 +8,7 @@ | |
| using Azure.DataApiBuilder.Config.Converters; | ||
| using Azure.DataApiBuilder.Config.NamingPolicies; | ||
| using Azure.DataApiBuilder.Config.ObjectModel; | ||
| using Azure.DataApiBuilder.Config.ObjectModel.Embeddings; | ||
| using Azure.DataApiBuilder.Core; | ||
| using Azure.DataApiBuilder.Core.Configurations; | ||
| using Azure.DataApiBuilder.Service; | ||
|
|
@@ -908,6 +909,27 @@ options.FileSinkRetainedFileCountLimit is not null || | |
| } | ||
| } | ||
|
|
||
| // Embeddings: Provider, Endpoint, ApiKey, Model, ApiVersion, Dimensions, TimeoutMs, Enabled | ||
| if (options.RuntimeEmbeddingsProvider is not null || | ||
| options.RuntimeEmbeddingsBaseUrl is not null || | ||
| options.RuntimeEmbeddingsApiKey is not null || | ||
| options.RuntimeEmbeddingsModel is not null || | ||
| options.RuntimeEmbeddingsApiVersion is not null || | ||
| options.RuntimeEmbeddingsDimensions is not null || | ||
| options.RuntimeEmbeddingsTimeoutMs is not null || | ||
| options.RuntimeEmbeddingsEnabled is not null) | ||
| { | ||
| bool status = TryUpdateConfiguredEmbeddingsValues(options, runtimeConfig?.Runtime?.Embeddings, out EmbeddingsOptions? updatedEmbeddingsOptions); | ||
| if (status && updatedEmbeddingsOptions is not null) | ||
| { | ||
| runtimeConfig = runtimeConfig! with { Runtime = runtimeConfig.Runtime! with { Embeddings = updatedEmbeddingsOptions } }; | ||
| } | ||
| else | ||
| { | ||
| return false; | ||
| } | ||
| } | ||
|
|
||
| return runtimeConfig != null; | ||
| } | ||
|
|
||
|
|
@@ -1522,6 +1544,97 @@ private static bool TryUpdateConfiguredFileOptions( | |
| } | ||
| } | ||
|
|
||
| /// <summary> | ||
| /// Attempts to update the embeddings configuration based on the provided options. | ||
| /// Creates a new EmbeddingsOptions object if the configuration is valid. | ||
| /// Provider, endpoint, and API key are required when configuring embeddings. | ||
| /// </summary> | ||
| /// <param name="options">The configuration options provided by the user.</param> | ||
| /// <param name="existingEmbeddingsOptions">The existing embeddings options from the runtime configuration.</param> | ||
| /// <param name="updatedEmbeddingsOptions">The resulting embeddings options if successful.</param> | ||
| /// <returns>True if the embeddings options were successfully configured; otherwise, false.</returns> | ||
| private static bool TryUpdateConfiguredEmbeddingsValues( | ||
| ConfigureOptions options, | ||
| EmbeddingsOptions? existingEmbeddingsOptions, | ||
| out EmbeddingsOptions? updatedEmbeddingsOptions) | ||
| { | ||
| updatedEmbeddingsOptions = null; | ||
|
|
||
| try | ||
| { | ||
| // Get values from options or fall back to existing configuration | ||
| EmbeddingProviderType? provider = options.RuntimeEmbeddingsProvider ?? existingEmbeddingsOptions?.Provider; | ||
| string? baseUrl = options.RuntimeEmbeddingsBaseUrl ?? existingEmbeddingsOptions?.BaseUrl; | ||
| string? apiKey = options.RuntimeEmbeddingsApiKey ?? existingEmbeddingsOptions?.ApiKey; | ||
| string? model = options.RuntimeEmbeddingsModel ?? existingEmbeddingsOptions?.Model; | ||
| string? apiVersion = options.RuntimeEmbeddingsApiVersion ?? existingEmbeddingsOptions?.ApiVersion; | ||
| int? dimensions = options.RuntimeEmbeddingsDimensions ?? existingEmbeddingsOptions?.Dimensions; | ||
| int? timeoutMs = options.RuntimeEmbeddingsTimeoutMs ?? existingEmbeddingsOptions?.TimeoutMs; | ||
| bool? enabled = options.RuntimeEmbeddingsEnabled.HasValue | ||
| ? options.RuntimeEmbeddingsEnabled.Value == CliBool.True | ||
| : existingEmbeddingsOptions?.Enabled; | ||
|
|
||
| // Validate required fields | ||
| if (provider is null) | ||
| { | ||
| _logger.LogError("Failed to configure embeddings: provider is required. Use --runtime.embeddings.provider to specify the provider (azure-openai or openai)."); | ||
| return false; | ||
| } | ||
|
|
||
| if (string.IsNullOrEmpty(baseUrl)) | ||
| { | ||
| _logger.LogError("Failed to configure embeddings: base-url is required. Use --runtime.embeddings.base-url to specify the provider base URL."); | ||
| return false; | ||
| } | ||
|
|
||
| if (string.IsNullOrEmpty(apiKey)) | ||
| { | ||
| _logger.LogError("Failed to configure embeddings: api-key is required. Use --runtime.embeddings.api-key to specify the authentication key."); | ||
| return false; | ||
| } | ||
|
|
||
| // Validate Azure OpenAI requires model/deployment name | ||
| if (provider == EmbeddingProviderType.AzureOpenAI && string.IsNullOrEmpty(model)) | ||
| { | ||
| _logger.LogError("Failed to configure embeddings: model/deployment name is required for Azure OpenAI provider. Use --runtime.embeddings.model to specify the deployment name."); | ||
| return false; | ||
| } | ||
|
|
||
| // Validate dimensions if provided | ||
| if (dimensions is not null && dimensions <= 0) | ||
| { | ||
| _logger.LogError("Failed to configure embeddings: dimensions must be a positive integer."); | ||
| return false; | ||
| } | ||
|
|
||
| // Validate timeout if provided | ||
| if (timeoutMs is not null && timeoutMs <= 0) | ||
| { | ||
| _logger.LogError("Failed to configure embeddings: timeout-ms must be a positive integer."); | ||
| return false; | ||
| } | ||
|
|
||
| // Create the embeddings options | ||
| updatedEmbeddingsOptions = new EmbeddingsOptions( | ||
| Provider: (EmbeddingProviderType)provider, | ||
| BaseUrl: baseUrl, | ||
| ApiKey: apiKey, | ||
|
Comment on lines
+1617
to
+1621
|
||
| Enabled: enabled, | ||
| Model: model, | ||
| ApiVersion: apiVersion, | ||
| Dimensions: dimensions, | ||
| TimeoutMs: timeoutMs); | ||
|
|
||
| _logger.LogInformation("Updated RuntimeConfig with Runtime.Embeddings configuration."); | ||
| return true; | ||
| } | ||
| catch (Exception ex) | ||
| { | ||
| _logger.LogError("Failed to update RuntimeConfig.Embeddings with exception message: {exceptionMessage}.", ex.Message); | ||
| return false; | ||
| } | ||
| } | ||
|
|
||
| /// <summary> | ||
| /// Parse permission string to create PermissionSetting array. | ||
| /// </summary> | ||
|
|
||
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
ConfigGeneratoronly triggers embeddings updates for provider/base-url/api-key/model/api-version/dimensions/timeout/enabled. The CLI also definesruntime.embeddings.endpoint.*andruntime.embeddings.health.*, but those flags are ignored here.Include the endpoint/health CLI flags in this condition so
dab configureactually updates them.