research/discover-topics
Topic Discovery workflow — find trending topics for a niche.
Category: research
Source: workflows/research/discover_topics.py
Input Schema
Section titled “Input Schema”| Field | Type | Default | Description |
|---|---|---|---|
min_score | integer | 5 | Minimum virality score to include |
niche | string | "" | Content niche (e.g. ‘AI tools’, ‘fitness’, ‘cooking’) |
num_topics | integer | 10 | Number of topics to return |
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. |
Output Schema
Section titled “Output Schema”| Field | Type | Default | Description |
|---|---|---|---|
best_topic | object | — | Highest-scoring topic |
discovery_context | string | "" | Formatted research context for downstream generation |
kind | object | — | Variant card shape: video / carousel / image / text. Surfaced on the per-variant entry of the run-output API and used by gallery UIs to pick the right layout. |
topics | object[] | — | Discovered topics with virality scores |
workflow | string | "discover-topics" | Workflow identifier |
Task Pipeline
Section titled “Task Pipeline”discover_topics| Task | Description |
|---|---|
discover_topics | Discover trending topics — delegates to SDK stage. |
Run-spec example
Section titled “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: research/discover-topics
# Optional fields — copy any line(s) under `input:` and uncomment to set:# Minimum virality score to include# min_score: 5## Content niche (e.g. 'AI tools', 'fitness', 'cooking')# niche: ""## Number of topics to return# num_topics: 10#
input: {}Run it locally:
fab-workflow --from-file my-run.yamlOr submit over the wire — the same file is the request body:
curl -X POST 'https://gofabric.dev/v1/workflows/runs?name=research/discover-topics' \ -H 'Authorization: Bearer fab_xxx' \ -H 'content-type: application/yaml' \ --data-binary @my-run.yamlEvery 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
Section titled “Warnings”- Task
discover_topicshas no Pydantic types — contract is opaque to consumers.