scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 108

fix(voyage): restore MongoDB routing on contextual endpoint and re-add voyage-4-nano after upstream merge

Browse source 
The upstream merge replaced the contextual config's get_complete_url with a
Voyage-only host and dropped voyage-4-nano from the model map. Reapply the
al- key routing via get_default_base_url and add voyage-4-nano (open-weight,
per docs.voyageai.com) so the branch keeps its task changes on top of upstream.
This commit is contained in:
fzowl 2026-09-18 15:23:58 +02:00
parent 1d25952d94
commit c86af7d8e4
3 changed files with 23 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
litellm/llms/voyage/embedding/transformation_contextual.py
View file

@ -11,7 +11,7 @@ import httpx
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.llms.base_llm.chat.transformation import BaseLLMException
from litellm.llms.base_llm.embedding.transformation import BaseEmbeddingConfig
from litellm.secret_managers.main import get_secret_str
from litellm.llms.voyage.common_utils import get_default_base_url, get_voyage_api_key
from litellm.types.llms.openai import AllEmbeddingInputValues, AllMessageValues
from litellm.types.utils import EmbeddingResponse, Usage
@ -58,7 +58,7 @@ class VoyageContextualEmbeddingConfig(BaseEmbeddingConfig):
if not api_base.endswith("/contextualizedembeddings"):
api_base = f"{api_base}/contextualizedembeddings"
return api_base
return "https://api.voyageai.com/v1/contextualizedembeddings"
return f"{get_default_base_url(api_key)}/contextualizedembeddings"
def get_supported_openai_params(self, model: str) -> list: # mutable-ok: base class signature
return ["encoding_format", "dimensions"]
@ -91,14 +91,8 @@ class VoyageContextualEmbeddingConfig(BaseEmbeddingConfig):
api_key: str | None = None,
api_base: str | None = None,
) -> dict:
if api_key is None:
api_key = (
get_secret_str("VOYAGE_API_KEY")
or get_secret_str("VOYAGE_AI_API_KEY")
or get_secret_str("VOYAGE_AI_TOKEN")
)
return {
"Authorization": f"Bearer {api_key}",
"Authorization": f"Bearer {get_voyage_api_key(api_key)}",
}
AUTO_CHUNK_SIZE: Final = 32000

10
litellm/model_prices_and_context_window_backup.json
View file

@ -60293,6 +60293,16 @@
"output_vector_size": 1024,
"source": "https://docs.voyageai.com/docs/pricing"
},
"voyage/voyage-4-nano": {
"input_cost_per_token": 0.0,
"litellm_provider": "voyage",
"max_input_tokens": 32000,
"max_tokens": 32000,
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1024,
"source": "https://docs.voyageai.com/docs/embeddings"
},
"voyage/voyage-code-4": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "voyage",

10
model_prices_and_context_window.json
View file

@ -60293,6 +60293,16 @@
"output_vector_size": 1024,
"source": "https://docs.voyageai.com/docs/pricing"
},
"voyage/voyage-4-nano": {
"input_cost_per_token": 0.0,
"litellm_provider": "voyage",
"max_input_tokens": 32000,
"max_tokens": 32000,
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1024,
"source": "https://docs.voyageai.com/docs/embeddings"
},
"voyage/voyage-code-4": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "voyage",