scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-22 00:31:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 51

init S3VectorsRAGIngestion as a supported ingestion provider for RAG API

Browse source
This commit is contained in:
Ishaan Jaffer 2026-01-27 13:55:06 -08:00
parent 7d5439adda
commit 2c3561e61e
2 changed files with 44 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
litellm/model_prices_and_context_window_backup.json
View file

@ -10232,6 +10232,48 @@
"mode": "completion",
"output_cost_per_token": 5e-07
},
"deepseek-v3-2-251201": {
"input_cost_per_token": 0.0,
"litellm_provider": "volcengine",
"max_input_tokens": 98304,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 0.0,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"glm-4-7-251222": {
"input_cost_per_token": 0.0,
"litellm_provider": "volcengine",
"max_input_tokens": 204800,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 0.0,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"kimi-k2-thinking-251104": {
"input_cost_per_token": 0.0,
"litellm_provider": "volcengine",
"max_input_tokens": 229376,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 0.0,
"supports_assistant_prefill": true,
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"doubao-embedding": {
"input_cost_per_token": 0.0,
"litellm_provider": "volcengine",

2
litellm/rag/main.py
View file

@ -31,6 +31,7 @@ from litellm.rag.ingestion.base_ingestion import BaseRAGIngestion
from litellm.rag.ingestion.bedrock_ingestion import BedrockRAGIngestion
from litellm.rag.ingestion.gemini_ingestion import GeminiRAGIngestion
from litellm.rag.ingestion.openai_ingestion import OpenAIRAGIngestion
from litellm.rag.ingestion.s3_vectors_ingestion import S3VectorsRAGIngestion
from litellm.rag.rag_query import RAGQuery
from litellm.types.rag import (
RAGIngestOptions,
@ -48,6 +49,7 @@ INGESTION_REGISTRY: Dict[str, Type[BaseRAGIngestion]] = {
"openai": OpenAIRAGIngestion,
"bedrock": BedrockRAGIngestion,
"gemini": GeminiRAGIngestion,
"s3_vectors": S3VectorsRAGIngestion,
}