global/formula-extract

Formula Extraction — analyze reference videos and extract reusable style DNA.

Category: global
Source: workflows/formula/extract.py

Input Schema

Field	Type	Default	Description
formula	object	—
formula_name	string	"untitled"
media_path	object	—
regenerate	object	—	When set, this run is a regeneration. Workflows may read direction / keep / extra_instructions to modulate prompts; the engine persists parent_run_id and parent_variant_index as run lineage columns.
variants	integer	1	Number of independent variant executions (1–10). When > 1, the engine runs the workflow N times with different sampling, producing N outputs.
video_path	object	—
video_paths	any[]	—

Output Schema

No schema defined.

Task Pipeline

prepare_videos → analyze_all_videos → synthesize_formula → save_formula

Task	Description
prepare_videos	Validate input and prepare video paths for analysis.
analyze_all_videos	Run the single-video analysis on each reference video, collect results.
synthesize_formula	Combine per-video analyses into a single formula.
save_formula	Persist the formula to a JSON file.

Run-spec example

Save the YAML below as my-run.yaml, edit the values, and run with the CLI or POST it to the API. Required fields are uncommented; optional knobs are documented above the input: block — copy any line under input: and uncomment to set.

workflow: global/formula-extract

# Optional fields — copy any line(s) under `input:` and uncomment to set:
#   formula: null
#
#   formula_name: untitled
#
#   media_path: null
#
#   video_path: null
#
#   video_paths: []
#

input: {}

Run it locally:

fab-workflow --from-file my-run.yaml

Or submit over the wire — the same file is the request body:

curl -X POST 'https://gofabric.dev/v1/workflows/runs?name=global/formula-extract' \
  -H 'Authorization: Bearer fab_xxx' \
  -H 'content-type: application/yaml' \
  --data-binary @my-run.yaml

Every workflow also accepts the universal WorkflowInput fields — variants (1–10 fan-out) and regenerate (creative-direction hints with run lineage). See Run-specs (YAML / TOML / JSON) for the full top-level shape (metadata, priority, bundle, parent, etc.).

Warnings

• Last user task save_formula has no Pydantic return type — workflow output schema is null. Declare a WorkflowOutput subclass and pass it to Flow(output=…) for a strict contract.