Document the new configuration and processing workflow

This commit is contained in:
2026-11-10 17:52:14 +00:00
parent 926fa26a31
commit ba1d5d2367
61 changed files with 832 additions and 765 deletions

View File

@@ -1,55 +1,34 @@
# Audita
Audita polishes transcript JSON using glossary-aware and LLM-backed correction
modules. It validates proposed corrections and produces corrected text plus
reports for review and subprocess integration.
Audita polishes transcript JSON with glossary-aware and LLM-backed correction
modules. It validates proposed edits and produces corrected text and reports for
review or subprocess integration.
## Quickstart
From a checkout, build with Go 1.26.0 or newer:
Build with Go 1.27.0 or newer:
```sh
go build -o ./bin/audita ./cmd/audita
```
Processing requires a reachable [compatible LLM endpoint](docs/integrations/openai-compatible-llm.md)
and access to a model you select. The [minimal config](examples/minimal-config.yml)
targets an unauthenticated local endpoint; edit its endpoint and
[local profiles](examples/profiles/local/) to match your service and models. The
[service example](examples/production-config.yml) demonstrates a named credential
reference and a shared backend. Set its referenced environment variable before
validating it. The [testing overlay](examples/overlays/testing.yml) selects both
role profiles, but model cost, speed, and quality depend on your provider choices.
Check configuration and profile selection offline:
Edit the synthetic endpoint and model in [examples/local/prompts.yml](examples/local/prompts.yml)
for a reachable OpenAI-compatible service. From `examples/local`, run the built
executable (adjust the executable path if needed):
```sh
./bin/audita config validate --config examples/minimal-config.yml
./bin/audita config print-effective --config examples/minimal-config.yml --view profiles
../../bin/audita config validate --config config.yml
../../bin/audita process --config config.yml --output corrected.json transcript.json
```
Run the included small input with the minimal config:
```sh
./bin/audita process examples/tiny-transcript.json \
--config examples/minimal-config.yml \
--glossary examples/tiny-glossary.yaml \
--output corrected.json
```
This makes LLM requests. Explicit setting flags override the selected file and
optional overlay; general environment setting overrides are no longer read.
By default the command writes `errors.yml`, `recoveries.yml`, and `report.md`
beside `corrected.json`. Use `--reporting=false` to suppress those files, or
`--debug` to retain detailed run artifacts under the configured debug work
directory. Model failures affecting some operations can still yield a completed
transcript with applied corrections; the summary and reports identify them.
See the [v2 migration guide](docs/migrations/v2.md) for old configurations.
Processing makes model requests. Reports are written beside the output by default;
recoverable model errors can appear in a completed run. The [example guide](examples/README.md)
includes service, overlay, prompt editing, preview, and shared glossary projects.
See the [v3 migration guide](docs/migrations/v3.md) for the configuration cutover.
## Documentation
- [CLI reference](docs/cli.md)
- [Configuration and maintained examples](docs/config.md)
- [CLI reference](docs/cli.md) and [configuration](docs/config.md)
- [Operations and artifact lifecycle](docs/operations.md)
- [Transcript and glossary inputs](docs/integrations/transcript-glossary-files.md)
- [Output files and report formats](docs/integrations/output-files.md)