flemming-it
86f191ca3e
'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>
124 lines
3.8 KiB
YAML
124 lines
3.8 KiB
YAML
schema_version: 3
|
|
provider: chain
|
|
name: text-summarize
|
|
version: 0.2.0
|
|
|
|
# Capability provided by this module.
|
|
provides:
|
|
- capability: text.summarize
|
|
version: 0.2.0
|
|
|
|
# Inputs the invoke function accepts.
|
|
inputs:
|
|
text:
|
|
type: text
|
|
description:
|
|
en: Source text to summarise.
|
|
de: Quelltext, der zusammengefasst werden soll.
|
|
style:
|
|
type: text
|
|
description:
|
|
en: |
|
|
Style / shape of the summary, e.g. "one paragraph",
|
|
"three bullet points", "a tweet". Defaults to
|
|
"one paragraph" when omitted.
|
|
de: |
|
|
Stil/Form der Zusammenfassung, z. B. "ein Absatz",
|
|
"drei Bulletpoints", "ein Tweet". Default ist
|
|
"ein Absatz".
|
|
language:
|
|
type: text
|
|
description:
|
|
en: |
|
|
Optional output language hint, e.g. "German", "ja-JP".
|
|
Empty = same language as the source.
|
|
de: |
|
|
Optionale Ausgabesprache, z. B. "German", "ja-JP".
|
|
Leer = gleiche Sprache wie die Quelle.
|
|
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 (e.g. "qwen2.5:14b").
|
|
de: Modell-Identifier (z. B. "qwen2.5:14b").
|
|
api_key:
|
|
type: text
|
|
description:
|
|
en: Optional bearer token for cloud-hosted endpoints.
|
|
de: Optionaler Bearer-Token für Cloud-Endpunkte.
|
|
|
|
# Outputs produced.
|
|
outputs:
|
|
summary:
|
|
type: text
|
|
description:
|
|
en: The summary text.
|
|
de: Die zusammengefasste Antwort.
|
|
style:
|
|
type: text
|
|
description:
|
|
en: Echo of the style input for downstream audit.
|
|
de: Echo des Style-Inputs für Downstream-Audit.
|
|
language:
|
|
type: text
|
|
description:
|
|
en: Echo of the language input.
|
|
de: Echo des Language-Inputs.
|
|
model_endpoint:
|
|
type: text
|
|
description:
|
|
en: Endpoint the summary was generated against.
|
|
de: Endpunkt, gegen den die Zusammenfassung 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 required.
|
|
permissions:
|
|
- "net: localhost"
|
|
- "net: 127.0.0.1"
|
|
- "net: api.openai.com"
|
|
- "net: api.anthropic.com"
|