From 2c3561e61e9c011c2bfd784d0e8ff87856dea97c Mon Sep 17 00:00:00 2001
From: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
Date: Tue, 27 Jan 2026 13:55:06 -0800
Subject: [PATCH] init S3VectorsRAGIngestion as a supported ingestion provider
 for RAG API

---
 ...odel_prices_and_context_window_backup.json | 42 +++++++++++++++++++
 litellm/rag/main.py                           |  2 +
 2 files changed, 44 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 7f33e96dbbb..4ac4159558f 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -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",
diff --git a/litellm/rag/main.py b/litellm/rag/main.py
index 620097f83dd..571f78f2f70 100644
--- a/litellm/rag/main.py
+++ b/litellm/rag/main.py
@@ -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,
 }