'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>
Port the multi-API client from llm.chat (llm.rs kept in lockstep):
the optional api input selects the dialect, default stays the
unchanged v0.1.x Ollama behavior. openai covers vLLM, LM Studio,
LiteLLM and cloud OpenAI; api-specific error hints; api_key sent
as Bearer (ollama/openai) or x-api-key (anthropic). model_digest
stays an Ollama-only best-effort probe and is documented as such.
Proven end-to-end against a hermetic OpenAI-wire fake (request
shape validated, response parsed) via a hub flow run.
Signed-off-by: flemming-it <sf@flemming.it>
Brings module.yaml in line with F∆I 0.12.0's capability naming
convention. The legacy schema_version 1 (with implicit provider)
still loads in 0.12.0 via the grace-period default, but this
bump makes the publisher identity explicit and unblocks
storage-layout migration via 'fai migrate'.
See fai/platform docs/reference/capability-namespaces.yaml +
docs/operations/migration-to-0.12.md.
Signed-off-by: flemming-it <sf@flemming.it>
Ollama-backed translation module — third real F∆I capability,
following text.extract and llm.chat. Used for the second leg of
a regulated document workflow (extract -> translate -> review
-> summarise).
Capability:
Inputs:
text : text (source text)
target_language : text (e.g. "German", "French")
source_language : text (optional hint; empty = auto)
endpoint : text (Ollama /api/chat URL)
model : text
api_key : text (optional)
Outputs:
translation : text
source_language : text (echo for audit)
target_language : text (echo for audit)
model_endpoint : text
model_name : text
model_digest : text (Ollama /api/show probe; empty
for non-Ollama or transient
failures)
Permissions: net to localhost / 127.0.0.1 / api.openai.com /
api.anthropic.com.
The translation prompt is conservative: a fixed system prompt
demands faithful translation with structure preservation and
emits no metadata, no quoting. The user prompt names the target
language and (when supplied) the source language. The LLM
client + digest-probe pattern is reused verbatim from llm-chat;
when a third module joins, the shared client moves into a small
crate.
14 host-side tests cover prompt-building, Ollama-shaped response
parsing, URL transform, digest extraction (top-level + nested),
end-to-end success, end-to-end probe-failure swallow, and
end-to-end skip-for-non-Ollama.
Wasm artifact verified to build with v1.0 fai:platform imports
baked in. Bootstrapped via 'fai new module text.translate'.
Signed-off-by: flemming-it <sf@flemming.it>
