[Embeddings][OpenAI] Support embeddings via engine.embeddings.create() #538
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Outdated suggestions cannot be applied.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.
This PR supports embedding model with
engine.embeddings.create()
.For running example, see
examples/embeddings
, where we can run with OpenAI API usingengine.embeddings.create()
, and we can also integrate with Langchain'sEmbeddingsInterface
andMemoryVectorStore
.Currently, only
snowflake-arctic-embed-s
andsnowflake-arctic-embed-m
are supported. We add the following models to the prebuilt model list:b32
means the model is compiled to support a maximum batch size of 32. If an input with more than 32 entries are provided, we will call multipleforward()
(e.g. if input has 67 entries, we forward 3 times). The larger the maximum batch size, the more memory it takes to load the model. Seevram_required_MB
inconfig.ts
for specifics.Besides, we currently do not allow loading multiple models in a single engine, making it a bit inconvenient for usecases like RAG. Engine with multiple models loaded will be supported soon.
Internal code changes
EmbeddingPipeline
insrc/embedding.ts
, parallel toLLMChatPipeline
inllm_chat.ts
engine.ts
, we determine which pipeline to load based onModelRecord.model_type
embedding()
inMLCEngineInterface
, hence supporting bothMLCEngine
andWebWorkerMLCEngine
src/openai_api_protocols/embedding.ts
Tested
b32
model, finishes with 2 iterationsexamples/embedding
is consistent withtransformers
in Python