DeepFellow DOCS

Discover a draft knowledge-graph ontology from sample files

Kick off ontology discovery from a handful of sample files, seeded with the current ontology.

Seeds from the project's approved ontology if it has one, else from the default ontology, so re-running discovery extends the live schema rather than dropping previously approved types. Overwrites the current draft; the previously approved ontology (if any), which GraphService actually uses, is left untouched until the draft is next saved or approved.

POST
/v1/graph/ontology/propose
Authorization[Bearer <token>]

In: header

Header Parameters

OpenAI-Organization?[string | null]

Organization Id from OpenAi compatible endpoint. Required to organization access or project access (with OpenAI-Project header) when logged as User or Admin User.

OpenAI-Project?[string | null]

Project Id from OpenAi compatible endpoint. Required to project access for organization api key or User / Admin User access with OpenAI-Organization

file_ids[array<string>]
Items1 <= items <= 10
boundaries?[string | null]

Free-text scope hint, e.g. 'legal contracts'.

Response Body

curl -X POST "https://deepfellow-server-host/v1/graph/ontology/propose" \  -H "OpenAI-Organization: string" \  -H "OpenAI-Project: string" \  -H "Content-Type: application/json" \  -d '{    "file_ids": [      "5eb7cf5a86d9755df3a6c593"    ]  }'
{}
{
  "detail": [
    {
      "loc": [
        "string"
      ],
      "msg": "string",
      "type": "string",
      "input": null,
      "ctx": {}
    }
  ]
}

We use cookies on our website. We use them to ensure proper functioning of the site and, if you agree, for purposes such as analytics, marketing, and targeting ads.