Run Pipeline

See also Pipelines for a detailed description of the available pipelines and their parameters.

A pipeline is a retrieval algorithm that belongs to a project. The Pipeline Editor allows you to test pipelines. Think of it as an alternative to testing the pipeline API with swagger.

flowchart TD
  Q["query parameters (JSON payload)"] --> P["pipeline"]
  I["project indexes / collections"] --> P
  P --> R["list of results with metadata"]

Here is an overview of the pipelines.

• tellusrSearch: Implements hybrid search. Returns a result list of TellusR documents matching the query with optional highlights, facets, filters.
• topChunkRag: Used for RAG workflows. Used by assistants created in TellusR.
• topDocRag: Also used for RAG workflows.
• documentStream: An iterator of the documents in the project. Can be used to extract all data.
• autocorrect: A pipeline for making corrections to misspellings.
• suggestDocs: A pipeline for recommending documents with title field that closely matches the query.
• inspectDocument: Fetches a whole document by its id field.

Example 1 (simple query)

In the example below we have entered a simple TellusR query against the tellusrSearch pipeline that implements the search algorithm.

Example 2 (query with more parameters and filters)

Below is a more complicated query. See the Swagger docs on documentation about query parameters.

{
  "q": "bygning",
  "hl": true,
  "pageStart": 0,
  "pageSize": 10,
  "semanticWeight": 0.5,
  "semantic.similarity.min": 0,
  "facet": {
    "category": {
      "type": "value",
      "limit": 10
    }
  },
  "fq": "*:* AND (category:(\"sak10\"))"
}

It makes a query, asks for highlights, uses pagination and requests facets.