mirror of
https://github.com/infiniflow/ragflow.git
synced 2026-07-06 03:18:36 +08:00
243d9ed281
## What - Add TogetherAI as a chat provider backed by its OpenAI-compatible `/v1/chat/completions` API - Register TogetherAI in the Go model factory and provider config - Support non-streaming chat, SSE streaming chat, model listing, and connection checks ## Notes - Uses the current TogetherAI OpenAI-compatible base URL `https://api.together.ai/v1` - Forwards documented chat parameters from `ChatConfig`: `max_tokens`, `temperature`, `top_p`, `stop`, and GPT-OSS `reasoning_effort` - Routes Together reasoning traces from `reasoning` / `reasoning_content` into `ReasonContent` ## Tests - `go test -vet=off -run TestTogetherAI -count=1 ./internal/entity/models` - `go test -vet=off -count=1 ./internal/entity/models` Refs #14736
35 lines
617 B
JSON
35 lines
617 B
JSON
{
|
|
"name": "TogetherAI",
|
|
"url": {
|
|
"default": "https://api.together.ai/v1"
|
|
},
|
|
"url_suffix": {
|
|
"chat": "chat/completions",
|
|
"models": "models"
|
|
},
|
|
"class": "together",
|
|
"models": [
|
|
{
|
|
"name": "openai/gpt-oss-20b",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
|
|
"max_tokens": 131072,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
},
|
|
{
|
|
"name": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
|
|
"max_tokens": 262144,
|
|
"model_types": [
|
|
"chat"
|
|
]
|
|
}
|
|
]
|
|
}
|