Adapter catalog

Every type: value supported in pipeline YAML. Grouped by workflow package.

For the full config shape of each adapter, see the adapter’s source file (linked) or call GET /api/v1/adapters/{type} which returns the JSON Schema.

Webscraper (factflow-webscraper)

`type:`	Purpose	Config class
`sitemap_parser`	Fetch a sitemap XML, extract URLs	(see `sitemap_adapter.py`)
`url_expander`	Fan-out: URL list → one message per URL	`URLExpanderConfig`
`web_scraper`	HTTP fetch with adaptive rate limiting	`WebScraperSettings`
`web_crawler`	JS-rendered fetch via crawl4ai	`WebCrawlerConfig`
`web_content_storage`	Persist HTML + metadata	`WebContentStorageConfig`

Markdown (factflow-markdown)

`type:`	Purpose	Config class
`storage_retriever`	Read bytes from storage by lineage ref	(see `pipeline_adapters.py`)
`html_to_markdown`	GitHub-flavoured HTML → markdown	(see `pipeline_adapters.py`)
`smart_segmenter`	Token-aware markdown splitting	(see `pipeline_adapters.py`)
`segment_publisher`	Fan-out: one message per segment	(see `pipeline_adapters.py`)
`markdown_storage_writer`	Persist canonical markdown + segments	`MarkdownStorageConfig`

Embeddings (factflow-embeddings)

`type:`	Purpose	Config class
`embedding_generator`	Generate embeddings, write to configured storage	`EmbeddingGeneratorConfig`

Boost (factflow-boost)

Adapters under factflow_boost.boost_processor:

`type:`	Purpose
`boost_enumerator`	Walk export folder, emit per-conversation messages
`boost_filter`	Drop conversations matching exclusion rules
`boost_norwegian_filter`	Language-gate to Norwegian
`boost_deduplicate`	MinHash near-duplicate removal
`boost_clustering`	Group similar conversations
`boost_catalog`	Build structured catalogue
`boost_storage_writer`	Persist catalogue
`boost_renderer`	Render to HTML / CSV / tree

Config classes live alongside each adapter in factflow_boost.boost_processor.

Translator (factflow-translator)

`type:`	Purpose	Config class
`llm_translator`	LLM-based translation with markdown preservation	`LLMTranslatorConfig`

Knowledge (factflow-knowledge)

`type:`	Purpose
`concept_detection`	LLM-based concept extraction
`concept_consolidation`	Merge concepts across sources; write to Avalon
`knowledge_diff`	Compare two concept maps, emit structured diff

SharePoint (factflow-sharepoint)

`type:`	Purpose
`sharepoint_ingest`	Pull documents from Microsoft Graph
`document_converter`	Convert Office docs to markdown

Replay (factflow-replay)

Replay isn’t composed into YAML pipelines as a type: — it’s invoked via POST /executions/{id}/replay or the CLI. See Replay guide.

Engine built-ins

A few utility adapters ship from factflow-engine itself:

`type:`	Purpose
`stage_storage`	Generic “write the current message to storage” step (used implicitly by most pipelines)

Introspection at runtime

The live catalogue with full config schemas:

factflow config validate --list-adapters

Or HTTP:

curl http://localhost:8000/api/v1/adapters
curl http://localhost:8000/api/v1/adapters/{type}

GET /api/v1/adapters/{type} returns the adapter’s config class as JSON Schema — usable for generating IDE autocomplete and tooling.

Pipeline YAML reference
Writing a new adapter
Per-package references under Reference → Packages