flemming-it
4d6acab6a1
'openai' reads as the cloud company — an operator running self-hosted vLLM should be able to write what they mean. The new value speaks the identical OpenAI wire (a guard test asserts the emitted request stays byte-identical to api: openai, so the alias can never drift into a dialect) but yields vLLM-specific error hints (vllm serve, port 8000) instead of generic OpenAI prose. Manifest + docs name the value in DE and EN. Signed-off-by: flemming-it <sf@flemming.it>
125 lines
4 KiB
YAML
125 lines
4 KiB
YAML
schema_version: 3
|
|
provider: chain
|
|
name: text-translate
|
|
version: 0.2.0
|
|
|
|
provides:
|
|
- capability: text.translate
|
|
version: 0.2.0
|
|
|
|
inputs:
|
|
text:
|
|
type: text
|
|
description:
|
|
en: Source text to translate.
|
|
de: Quelltext, der übersetzt werden soll.
|
|
target_language:
|
|
type: text
|
|
description:
|
|
en: |
|
|
Target language name in plain English (e.g. "German",
|
|
"French", "ja-JP" — anything the configured LLM
|
|
understands).
|
|
de: |
|
|
Zielsprache in Klartext (z. B. "German", "French",
|
|
"ja-JP" — alles was das konfigurierte LLM versteht).
|
|
source_language:
|
|
type: text
|
|
description:
|
|
en: |
|
|
Optional source language hint. Empty = let the model
|
|
auto-detect.
|
|
de: |
|
|
Optionaler Hinweis zur Quellsprache. Leer = das Modell
|
|
erkennt sie selbst.
|
|
endpoint:
|
|
type: text
|
|
description:
|
|
en: |
|
|
Chat endpoint URL matching the selected api:
|
|
ollama "http://localhost:11434/api/chat",
|
|
openai "http://localhost:8000/v1/chat/completions"
|
|
(vLLM etc.), anthropic "https://.../v1/messages".
|
|
de: |
|
|
Chat-Endpunkt-URL passend zum gewählten api:
|
|
ollama "http://localhost:11434/api/chat",
|
|
openai "http://localhost:8000/v1/chat/completions"
|
|
(vLLM u. a.), anthropic "https://.../v1/messages".
|
|
api:
|
|
type: text
|
|
description:
|
|
en: |
|
|
Optional wire format: "ollama" (default), "vllm"
|
|
(self-hosted vLLM), "openai" (OpenAI or other
|
|
OpenAI-compatible servers such as LM Studio), or
|
|
"anthropic" (Messages API). vllm and openai speak the
|
|
same wire; the separate value exists so you can write
|
|
what you mean and get vLLM-specific hints. Empty = ollama.
|
|
de: |
|
|
Optionales Wire-Format: "ollama" (Default), "vllm"
|
|
(selbst gehostetes vLLM), "openai" (OpenAI oder andere
|
|
OpenAI-kompatible Server wie LM Studio) oder "anthropic"
|
|
(Messages API). vllm und openai sprechen dieselbe Wire;
|
|
der eigene Wert existiert, damit Du schreibst, was Du
|
|
meinst, und vLLM-spezifische Hinweise bekommst.
|
|
Leer = ollama.
|
|
model:
|
|
type: text
|
|
description:
|
|
en: Model identifier as registered with the endpoint (e.g. "qwen2.5:14b").
|
|
de: Modell-Identifier wie am Endpunkt registriert (z. B. "qwen2.5:14b").
|
|
api_key:
|
|
type: text
|
|
description:
|
|
en: |
|
|
Optional API key. Sent as "Authorization: Bearer" for
|
|
ollama/openai and as "x-api-key" for anthropic. Empty
|
|
for local endpoints.
|
|
de: |
|
|
Optionaler API-Key. Bei ollama/openai als
|
|
"Authorization: Bearer", bei anthropic als "x-api-key"
|
|
gesendet. Leer für lokale Endpunkte.
|
|
|
|
outputs:
|
|
translation:
|
|
type: text
|
|
description:
|
|
en: The translated text.
|
|
de: Der übersetzte Text.
|
|
source_language:
|
|
type: text
|
|
description:
|
|
en: Echo of the source-language input for downstream audit.
|
|
de: Echo des source_language-Inputs für Downstream-Audit.
|
|
target_language:
|
|
type: text
|
|
description:
|
|
en: Echo of the target-language input.
|
|
de: Echo des target_language-Inputs.
|
|
model_endpoint:
|
|
type: text
|
|
description:
|
|
en: Endpoint the translation was generated against.
|
|
de: Endpunkt, gegen den die Übersetzung erzeugt wurde.
|
|
model_name:
|
|
type: text
|
|
description:
|
|
en: Model identifier as supplied to the LLM API.
|
|
de: An die LLM-API übergebenes Modell.
|
|
model_digest:
|
|
type: text
|
|
description:
|
|
en: |
|
|
SHA-256 digest of the served model, best-effort probe.
|
|
Ollama only — empty for other endpoints (OpenAI / vLLM /
|
|
Anthropic expose no digest API).
|
|
de: |
|
|
SHA-256-Digest des bedienten Modells (Best-Effort-Probe).
|
|
Nur bei Ollama — leer bei anderen Endpunkten (OpenAI /
|
|
vLLM / Anthropic bieten keine Digest-API).
|
|
|
|
permissions:
|
|
- "net: localhost"
|
|
- "net: 127.0.0.1"
|
|
- "net: api.openai.com"
|
|
- "net: api.anthropic.com"
|