global/embeddings

Embedding pipeline — generate vector embeddings for text/content.

Category: global
Source: workflows/ai/embeddings.py

Input Schema

Field	Type	Default	Description
embedding_model	string	"auto"
openai_api_key	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.
texts	any[]	—
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.

Output Schema

No schema defined.

Task Pipeline

generate_embeddings

Task	Description
generate_embeddings	Generate embeddings for a list of texts.

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/embeddings

# Optional fields — copy any line(s) under `input:` and uncomment to set:
#   embedding_model: auto
#
#   openai_api_key: null
#
#   texts: []
#

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/embeddings' \
  -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 generate_embeddings has no Pydantic return type — workflow output schema is null. Declare a WorkflowOutput subclass and pass it to Flow(output=…) for a strict contract.