Skip to content

Feature(LiteLLM): Wire LiteLLM Docker profile with application config overrides (provider and embedder) #533

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
marazik wants to merge 3 commits into
base: main
Choose a base branch
from
+243 −0
Open

Feature(LiteLLM): Wire LiteLLM Docker profile with application config overrides (provider and embedder) #533

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7cc2425
feature(litellm): integrate docker profile and config overrides
marazik Jun 3, 2026
4f6161d
Removed the context window size (`num_ctx`) parameter
marazik Aug 19, 2026
9b5f246
Removed the redundant `initialize_kwargs` block from LiteLLM embedder…
marazik Aug 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 23 additions & 0 deletions api/config/embedder.litellm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
{
"embedder_ollama": {
"client_class": "OllamaClient",
"model_kwargs": {
"model": "nomic-embed-text"
}
},
"embedder": {
"client_class": "LiteLLMClient",
"batch_size": 10,
Comment thread
marazik marked this conversation as resolved.
"model_kwargs": {
"model": "nomic-embed-text"
}
},
"retriever": {
"top_k": 20
},
"text_splitter": {
"split_by": "word",
"chunk_size": 350,
"chunk_overlap": 100
}
}
217 changes: 217 additions & 0 deletions api/config/generator.litellm.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,217 @@
{
"default_provider": "litellm",
"providers": {
"dashscope": {
"default_model": "qwen-plus",
"supportsCustomModel": true,
"models": {
"qwen-plus": {
"temperature": 0.7,
"top_p": 0.8
},
"qwen-turbo": {
"temperature": 0.7,
"top_p": 0.8
},
"deepseek-r1": {
"temperature": 0.7,
"top_p": 0.8
}
}
},
"google": {
"default_model": "gemini-2.5-flash",
"supportsCustomModel": true,
"models": {
"gemini-2.5-flash": {
"temperature": 1.0,
"top_p": 0.8,
"top_k": 20
},
"gemini-2.5-flash-lite": {
"temperature": 1.0,
"top_p": 0.8,
"top_k": 20
},
"gemini-2.5-pro": {
"temperature": 1.0,
"top_p": 0.8,
"top_k": 20
}
}
},
"openai": {
"default_model": "gpt-5-nano",
"supportsCustomModel": true,
"models": {
"gpt-5": {
"temperature": 1.0
},
"gpt-5-nano": {
"temperature": 1.0
},
"gpt-5-mini": {
"temperature": 1.0
},
"gpt-4o": {
"temperature": 0.7,
"top_p": 0.8
},
"gpt-4.1": {
"temperature": 0.7,
"top_p": 0.8
},
"o1": {
"temperature": 0.7,
"top_p": 0.8
},
"o3": {
"temperature": 1.0
},
"o4-mini": {
"temperature": 1.0
}
}
},
"litellm": {
"default_model": "qwen3:1.7b",
"supportsCustomModel": true,
"models": {
"qwen3:1.7b": {
"temperature": 0.7,
"top_p": 0.8
},
"llama3:8b": {
"temperature": 0.7,
"top_p": 0.8
},
"qwen3:8b": {
"temperature": 0.7,
"top_p": 0.8
}
Comment thread
marazik marked this conversation as resolved.
}
},
"openrouter": {
"default_model": "openai/gpt-5-nano",
"supportsCustomModel": true,
"models": {
"openai/gpt-5-nano": {
"temperature": 0.7,
"top_p": 0.8
},
"openai/gpt-4o": {
"temperature": 0.7,
"top_p": 0.8
},
"deepseek/deepseek-r1": {
"temperature": 0.7,
"top_p": 0.8
},
"openai/gpt-4.1": {
"temperature": 0.7,
"top_p": 0.8
},
"openai/o1": {
"temperature": 0.7,
"top_p": 0.8
},
"openai/o3": {
"temperature": 1.0
},
"openai/o4-mini": {
"temperature": 1.0
},
"anthropic/claude-3.7-sonnet": {
"temperature": 0.7,
"top_p": 0.8
},
"anthropic/claude-3.5-sonnet": {
"temperature": 0.7,
"top_p": 0.8
}
}
},
"ollama": {
"default_model": "qwen3:1.7b",
"supportsCustomModel": true,
"models": {
"qwen3:1.7b": {
"options": {
"temperature": 0.7,
"top_p": 0.8,
"num_ctx": 32000
}
},
"llama3:8b": {
"options": {
"temperature": 0.7,
"top_p": 0.8,
"num_ctx": 8000
}
},
"qwen3:8b": {
"options": {
"temperature": 0.7,
"top_p": 0.8,
"num_ctx": 32000
}
}
}
},
"bedrock": {
"client_class": "BedrockClient",
"default_model": "anthropic.claude-3-sonnet-20240229-v1:0",
"supportsCustomModel": true,
"models": {
"anthropic.claude-3-sonnet-20240229-v1:0": {
"temperature": 0.7,
"top_p": 0.8
},
"anthropic.claude-3-haiku-20240307-v1:0": {
"temperature": 0.7,
"top_p": 0.8
},
"anthropic.claude-3-opus-20240229-v1:0": {
"temperature": 0.7,
"top_p": 0.8
},
"amazon.titan-text-express-v1": {
"temperature": 0.7,
"top_p": 0.8
},
"cohere.command-r-v1:0": {
"temperature": 0.7,
"top_p": 0.8
},
"ai21.j2-ultra-v1": {
"temperature": 0.7,
"top_p": 0.8
}
}
},
"azure": {
"client_class": "AzureAIClient",
"default_model": "gpt-4o",
"supportsCustomModel": true,
"models": {
"gpt-4o": {
"temperature": 0.7,
"top_p": 0.8
},
"gpt-4": {
"temperature": 0.7,
"top_p": 0.8
},
"gpt-35-turbo": {
"temperature": 0.7,
"top_p": 0.8
},
"gpt-4-turbo": {
"temperature": 0.7,
"top_p": 0.8
}
}
}
}
}

3 changes: 3 additions & 0 deletions docker-compose-litellm.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,6 +53,9 @@ services:
volumes:
- ~/.adalflow:/root/.adalflow # Persist repository and embedding data
- ./api/logs:/app/api/logs # Persist log files across container restarts
# LiteLLM-specific config overrides
- ./api/config/generator.litellm.json:/app/api/config/generator.json:ro
- ./api/config/embedder.litellm.json:/app/api/config/embedder.json:ro
# Resource limits for docker-compose up (not Swarm mode)
mem_limit: 6g
mem_reservation: 2g
Expand Down
Loading