holetron-lab/fleet-memory
1
0
Fork 0
Code Releases Packages Activity Actions

feat: add support for ark and volcano LLM providers (#714)

Browse source 
- Add 'ark' and 'volcano' as valid LLM providers (both are aliases for Volcano Engine)
- Set default model to 'doubao-pro-32k' for both providers
- Add them to OpenAICompatibleLLM provider list
- Exclude from json_object response format support

Co-authored-by: yishun.eason <yishun.eason@bytedance.com>
This commit is contained in:
shun yi 2026-03-27 00:14:13 +08:00 committed by GitHub
parent 105cdf1fbf
commit 417fac61e4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 7 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.env.example
View file

@ -2,7 +2,7 @@
# Copy this file to .env and fill in your values # Copy this file to .env and fill in your values
# LLM Configuration (Required) # LLM Configuration (Required)
# Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai, minimax # Supported providers: openai, groq, ollama, gemini, anthropic, lmstudio, vertexai, minimax, volcano
HINDSIGHT_API_LLM_PROVIDER=openai HINDSIGHT_API_LLM_PROVIDER=openai
HINDSIGHT_API_LLM_API_KEY=your-api-key-here HINDSIGHT_API_LLM_API_KEY=your-api-key-here
HINDSIGHT_API_LLM_MODEL=gpt-4o-mini HINDSIGHT_API_LLM_MODEL=gpt-4o-mini

1
hindsight-api-slim/hindsight_api/config.py
View file

@ -368,6 +368,7 @@ PROVIDER_DEFAULT_MODELS = {
"none": "none", "none": "none",
"litellm": "gpt-4o-mini", "litellm": "gpt-4o-mini",
"bedrock": "us.amazon.nova-2-lite-v1:0", "bedrock": "us.amazon.nova-2-lite-v1:0",
"volcano": "doubao-pro-32k",
} }
DEFAULT_LLM_MODEL = "gpt-4o-mini" # Fallback if provider not in table DEFAULT_LLM_MODEL = "gpt-4o-mini" # Fallback if provider not in table
DEFAULT_LLM_MAX_CONCURRENT = 32 DEFAULT_LLM_MAX_CONCURRENT = 32

3
hindsight-api-slim/hindsight_api/engine/llm_wrapper.py
View file

@ -261,7 +261,7 @@ def create_llm_provider(
reasoning_effort=reasoning_effort, reasoning_effort=reasoning_effort,
) )
elif provider_lower in ("openai", "groq", "ollama", "lmstudio", "minimax"): elif provider_lower in ("openai", "groq", "ollama", "lmstudio", "minimax", "volcano"):
return OpenAICompatibleLLM( return OpenAICompatibleLLM(
provider=provider, provider=provider,
api_key=api_key, api_key=api_key,
@ -334,6 +334,7 @@ class LLMProvider:
"minimax", "minimax",
"litellm", "litellm",
"bedrock", "bedrock",
"volcano",
] ]
if self.provider not in valid_providers: if self.provider not in valid_providers:
raise ValueError(f"Invalid LLM provider: {self.provider}. Must be one of: {', '.join(valid_providers)}") raise ValueError(f"Invalid LLM provider: {self.provider}. Must be one of: {', '.join(valid_providers)}")

6
hindsight-api-slim/hindsight_api/engine/providers/openai_compatible_llm.py
View file

@ -98,7 +98,7 @@ class OpenAICompatibleLLM(LLMInterface):
super().__init__(provider, api_key, base_url, model, reasoning_effort, **kwargs) super().__init__(provider, api_key, base_url, model, reasoning_effort, **kwargs)
# Validate provider # Validate provider
valid_providers = ["openai", "groq", "ollama", "lmstudio", "minimax"] valid_providers = ["openai", "groq", "ollama", "lmstudio", "minimax", "volcano"]
if self.provider not in valid_providers: if self.provider not in valid_providers:
raise ValueError(f"OpenAICompatibleLLM only supports: {', '.join(valid_providers)}. Got: {self.provider}") raise ValueError(f"OpenAICompatibleLLM only supports: {', '.join(valid_providers)}. Got: {self.provider}")
@ -316,8 +316,8 @@ class OpenAICompatibleLLM(LLMInterface):
first_msg = call_params["messages"][0] first_msg = call_params["messages"][0]
if isinstance(first_msg, dict) and isinstance(first_msg.get("content"), str): if isinstance(first_msg, dict) and isinstance(first_msg.get("content"), str):
first_msg["content"] = schema_msg + "\n\n" + first_msg["content"] first_msg["content"] = schema_msg + "\n\n" + first_msg["content"]
if self.provider not in ("lmstudio", "ollama"): if self.provider not in ("lmstudio", "ollama", "volcano"):
# LM Studio and Ollama don't support json_object response format reliably # LM Studio, Ollama and Volcano don't support json_object response format reliably
call_params["response_format"] = {"type": "json_object"} call_params["response_format"] = {"type": "json_object"}
last_exception = None last_exception = None