Skip to content

feat: add Requesty as an OpenAI-compatible LLM provider #516

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
Thibaultjaigu wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

feat: add Requesty as an OpenAI-compatible LLM provider #516

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
3 changes: 2 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,14 +158,15 @@ agn connect my-aider <workspace-token> # connect Aider into a works

**Provider, model & key.** `AIDER_PROVIDER` decides which provider environment
variable your `LLM_API_KEY` is injected into. It accepts `auto` (default),
`openai`, `anthropic`, `openrouter`, `gemini`, `deepseek`, or
`openai`, `anthropic`, `openrouter`, `requesty`, `gemini`, `deepseek`, or
`openai-compatible`:

| `AIDER_PROVIDER` | Key injected as | Notes |
|---|---|---|
| `anthropic` | `ANTHROPIC_API_KEY` | e.g. `AIDER_MODEL=sonnet` / `opus` / `claude-3-5-sonnet-20241022` |
| `openai` | `OPENAI_API_KEY` | e.g. `AIDER_MODEL=gpt-4o` |
| `openrouter` | `OPENROUTER_API_KEY` | e.g. `AIDER_MODEL=openrouter/anthropic/claude-3.5-sonnet` |
| `requesty` | `REQUESTY_API_KEY` | e.g. `AIDER_MODEL=requesty/openai/gpt-4o` |
| `gemini` | `GEMINI_API_KEY` | e.g. `AIDER_MODEL=gemini/gemini-1.5-pro` |
| `deepseek` | `DEEPSEEK_API_KEY` | e.g. `AIDER_MODEL=deepseek/deepseek-chat` |
| `openai-compatible` | `OPENAI_API_KEY` + `OPENAI_API_BASE` | **requires `LLM_BASE_URL`**; the model is normalized to `openai/<model>` |
Expand Down
1 change: 1 addition & 0 deletions llms.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -579,6 +579,7 @@ This allows you to configure LLM settings once at the environment level rather t
| `together` | `TOGETHER_API_KEY` | meta-llama/Llama-2-70b-chat-hf |
| `perplexity` | `PERPLEXITY_API_KEY` | llama-3.1-sonar-huge-128k-online |
| `openrouter` | `OPENROUTER_API_KEY` | (any model via OpenRouter) |
| `requesty` | `REQUESTY_API_KEY` | (any model via Requesty) |
| `bedrock` | `AWS_ACCESS_KEY_ID` | anthropic.claude-3-5-sonnet |
| `custom` | `CUSTOM_API_KEY` | (requires DEFAULT_LLM_BASE_URL) |

Expand Down
9 changes: 9 additions & 0 deletions sdk/src/openagents/config/llm_configs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ class LLMProviderType(str, Enum):
PERPLEXITY = "perplexity"
GROQ = "groq"
OPENROUTER = "openrouter"
REQUESTY = "requesty"
MINIMAX = "minimax"
LITELLM = "litellm"
CUSTOM = "custom" # Custom OpenAI-compatible endpoint
Expand Down Expand Up @@ -186,6 +187,13 @@ class LLMProviderType(str, Enum):
"models": [], # User specifies model name (e.g., "anthropic/claude-3-opus")
"API_KEY_ENV_VAR": "OPENROUTER_API_KEY",
},
# Requesty (OpenAI-compatible LLM gateway)
"requesty": {
"provider": "generic",
"api_base": "https://router.requesty.ai/v1",
"models": [], # User specifies model name (e.g., "openai/gpt-4o-mini")
"API_KEY_ENV_VAR": "REQUESTY_API_KEY",
},
# MiniMax
"minimax": {
"provider": "minimax",
Expand Down Expand Up @@ -495,6 +503,7 @@ def create_model_provider(
"perplexity",
"groq",
"openrouter",
"requesty",
]:
# Use predefined API base if not provided
if not api_base and provider in MODEL_CONFIGS:
Expand Down
Loading