feat: add LiteLLM as embedding provider

[RheagalFire]

Summary

• Adds LiteLLM as a new semantic embedding provider, enabling access to 100+ embedding providers (OpenAI, Cohere, Azure, Bedrock, etc.) via a single unified SDK
• New LiteLLMEmbeddingProvider implementing the EmbeddingProvider protocol, following the exact same pattern as OpenAIEmbeddingProvider
• Wired into create_embedding_provider() factory with provider_name == "litellm"

Changes

• src/basic_memory/repository/litellm_provider.py - new LiteLLMEmbeddingProvider with:
  • litellm.aembedding() for async embedding
  • drop_params=True for cross-provider kwargs compatibility
  • Batched requests with configurable concurrency (same as OpenAI provider)
  • Dimension validation
• src/basic_memory/repository/embedding_provider_factory.py - added elif provider_name == "litellm" branch
• pyproject.toml - added litellm>=1.60.0,<2.0.0 to dependencies
• tests/repository/test_litellm_provider.py - 13 unit tests (all passing)

Tests

Unit tests (13/13 passing):

$ pytest tests/repository/test_litellm_provider.py -v --no-cov --noconftest
test_file_exists PASSED                                                                                                                                                                                            
test_has_litellm_embedding_provider_class PASSED                                                                                                                                                                   
test_has_embed_documents_method PASSED                                                                                                                                                                             
test_embed_documents_is_async PASSED                                                                                                                                                                               
test_uses_drop_params_true PASSED
test_uses_litellm_aembedding PASSED
test_has_runtime_log_attrs PASSED                                                                                                                                                                                  
test_default_model_in_source PASSED
test_litellm_branch_in_factory PASSED                                                                                                                                                                              
test_imports_litellm_provider PASSED
test_aembedding_called_with_drop_params PASSED                                                                                                                                                                     
test_aembedding_forwards_api_key PASSED
test_aembedding_response_has_vectors PASSED                                                                                                                                                                        
13 passed in 0.04s

Example usage

# In basic-memory config
[semantic]                                                                                                                                                                                                         
provider = "litellm"
model = "openai/text-embedding-3-small"
# or: "cohere/embed-english-v3.0", "azure/my-deployment", etc.                                                                                                                                                     

from basic_memory.repository.litellm_provider import LiteLLMEmbeddingProvider

provider = LiteLLMEmbeddingProvider(
    model_name="openai/text-embedding-3-small",                                                                                                                                                                    
    dimensions=1536,
    # LiteLLM reads OPENAI_API_KEY, COHERE_API_KEY, etc. from env automatically                                                                                                                                    
)                                                                                                                                                                                                                  
                                                                                                                                                                                                                   
vectors = await provider.embed_documents(["hello world", "basic memory"])                                                                                                                                          
query_vec = await provider.embed_query("search term")                                                                                                                                                              

See https://docs.litellm.ai/docs/embedding/supported_embedding for all supported embedding models.

Impact

• Additive only, existing providers (fastembed, openai) untouched
• litellm added as dependency in pyproject.toml
• drop_params=True silently drops provider-unsupported kwargs
• Same batching, concurrency, and dimension validation as OpenAIEmbeddingProvider
• Factory auto-discovers via provider_name == "litellm" config

[CLAassistant]

All committers have signed the CLA.

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: c029eb3b86

ℹ️ About Codex in GitHub

Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[chatgpt-codex-connector]

Map the built-in default model for LiteLLM

When users switch only semantic_embedding_provider to litellm, BasicMemoryConfig still supplies the non-empty default model bge-small-en-v1.5, so this or never selects the LiteLLM provider default. The factory then instantiates LiteLLMEmbeddingProvider(model_name="bge-small-en-v1.5") instead of a LiteLLM-routable model such as openai/text-embedding-3-small, making the new provider fail for the documented minimal configuration; mirror the OpenAI branch's remapping of the FastEmbed default or otherwise treat it as unset.

Useful? React with 👍 / 👎.

[RheagalFire]

cc @phernandez