Create a new AzureEmbedding instance with an API key
API key string
Protected_Protected property to store additional provider-specific settings
Get the current additional settings
ProtectedapiOnly sub-classes can access the API key
ProtectedClientGet the Azure AI client, initializing if necessary
ProtectedembedBase delay (ms) for exponential backoff between per-text retries: delay = base * 2^(n-1).
Get the Azure endpoint URL from additional settings
ProtectedmaxMax in-flight EmbedText calls for the default (non-batch) path. Override to tune.
Only the per-text fallback is throttled this way — the native embedBatch path sends all texts in ONE request, so there is nothing to bound. That asymmetry is intentional: N small calls need a concurrency ceiling; a single batched call does not.
ProtectedmaxExtra retry attempts per text on the default (non-batch) path, on top of the initial attempt.
0 disables retry. Retrying each text a few times before giving up stops one transient 429/500
from failing the whole batch (whose failure rate otherwise scales with the text count N).
Native batch endpoint: Azure AI Inference embeds an array of inputs in one request.
Clear all additional settings and reset the client
ProtectedembedCreate embeddings for multiple texts using Azure AI
Embedding parameters
Embedding result
Embeds text and/or interleaved media content into a single fused vector.
Default behavior: text-only content is delegated to EmbedText; if any non-text block is present, throws — because the base provider can't embed media. Multimodal providers (e.g. GeminiEmbedding) should override this method.
ProtectedembedDefault (non-batch) path: fans out one EmbedText call per text with bounded concurrency, preserving order. The 1:1 vector/text count is enforced by the dispatcher (EmbedTexts).
Each text is first retried with bounded exponential backoff (retryEmbedText) so a lone transient failure doesn't sink the batch; only a text that STILL fails after its retries counts as failed.
ERROR CONTRACT (deliberate — change here if a different policy is wanted): mirrors the
per-provider Gemini fix. On ANY per-text failure that survives retry (EmbedText throws OR yields
an empty vector) we return an EMPTY result rather than throwing, so batch pipelines that don't
wrap EmbedTexts (e.g. EntityVectorSyncer) degrade gracefully instead of aborting. To make it
fully fail-loud instead, replace the two emptyEmbedTextsResult(...) returns below with throw.
Create embeddings for a single text using Azure AI
Embedding parameters
Embedding result
Embeds an array of texts, returning exactly ONE vector per input text, in input order.
DISPATCHES on SupportsBatchEmbeddings: providers with a native batch endpoint set it to
true and implement embedBatch; everyone else gets the safe per-text fallback in
embedPerText. (A provider may still override this method directly for fully custom
behavior.)
Whichever path runs, the result is hard-asserted to be 1:1 with the inputs (an intentional
empty result — the per-text graceful-degrade — is allowed): a native embedBatch that drops
or reorders vectors, or any other collapse, throws here rather than letting a misaligned array
reach index-based consumers (e.g. EntityVectorSyncer).
Get available embedding models
List of available embedding models
Declares which non-text mime types this provider's embedding model can embed. null = text-only (the default). Multimodal providers override this. Mirrors BaseLLM.GetFileCapabilities().
ProtectedretryRuns a single-text embed attempt with bounded exponential-backoff retry. A transient failure —
attempt throws, or returns an empty/missing vector — is retried up to maxEmbedTextsRetries
times, sleeping embedRetryBaseDelayMs * 2^(n-1) between tries. Returns the first successful
result; after the final attempt returns whatever it produced (or rethrows its error) so the caller's
existing empty-vector / throw handling still applies. This is what keeps one transient 429/500 from
failing the whole batch.
ProtectedrunRuns fn over items with at most maxConcurrency in flight at once, preserving order.
The per-item await inside each worker is what bounds concurrency; parallelism comes from
running up to maxConcurrency workers at the same time.
Set additional provider-specific settings
Azure-specific settings
ProtectedsleepSleep helper for retry backoff, isolated so tests can override embedRetryBaseDelayMs to avoid real delays.
ProtectedValidateThrows if content contains a media block whose mime type the model can't embed.
Text-only content always passes. Called by multimodal providers at the top of EmbedContent.
Implementation of Azure AI Embedding Model AzureEmbedding