Create a project

Create a new project. Returns the created project on success.

On this page

HTTP request 

POST https://api.parsewise.ai/api/v1/projects/

Request Header

Name Required Type Description
X-API-Key Yes string API key with the pw_live_ prefix. See Authentication.

Request Body

Supported content types: application/json, application/x-www-form-urlencoded, multipart/form-data.

Name Required Type Description
name Yes string Human-readable name shown in the UI and in lists.
description No string Short description of what the project covers.
reference_date No string (date) (nullable) Reference date used by agents that need a “today” anchor (e.g. relative date extractions). Defaults to the date the project was created.
per_document_mode No boolean When true, extraction results are scoped per-document rather than aggregated across the project. Used for projects where each document represents a separate subject (e.g. one contract per file).
per_tag_mode No boolean When true, extraction results are grouped per tag value. Should not be combined with per_document_mode.

Responses

Status Type Description
201 V1Project —

Security

  • ApiKeyAuth — apiKey — in X-API-Key header. API key with pw_live_ prefix.

Python example 

import os
import requests

API_KEY = os.environ["PARSEWISE_API_KEY"]
BASE_URL = "https://api.parsewise.ai/api/v1"

body = {
    "name": "...",
    "description": "...",  # optional
    "reference_date": "YYYY-MM-DD",  # optional
    "per_document_mode": False,  # optional
    "per_tag_mode": False,  # optional
}

resp = requests.post(
    f"{BASE_URL}/projects/",
    headers={"X-API-Key": API_KEY},
    json=body,
)
resp.raise_for_status()
print(resp.json() if resp.content else None)

Definitions

V1Project

A project: the top-level container that groups documents, agents, and extraction results.

Returned by GET /projects/ and GET /projects/{project_id}/; also accepted as the request body for PATCH /projects/{project_id}/, where only the fields you supply are updated. Server-managed fields such as id, created_at, last_visited_at, document_count, and agent_count are read-only.

Name Required Type Description
id Yes string (uuid) Stable identifier for the project (UUID).
name Yes string Human-readable name shown in the UI and in lists.
description No string Short description of what the project covers.
last_visited_at Yes string (date-time) (nullable) Timestamp of the most recent visit to this project.
reference_date No string (date) (nullable) Reference date used by agents that need a “today” anchor (e.g. relative date extractions). Defaults to the date the project was created.
per_document_mode No boolean When true, extraction results are scoped per-document rather than aggregated across the project. Used for projects where each document represents a separate subject (e.g. one contract per file).
per_tag_mode No boolean When true, extraction results are grouped per tag value. Should not be combined with per_document_mode.
document_count Yes integer Number of documents currently in the project.
agent_count Yes integer Number of non-draft agents configured on the project.
is_pinned No boolean Whether the project is pinned to the top of the project list.
project_modules Yes any Per-project overrides for which application modules are enabled, keyed by module name with boolean values. A missing key falls back to the organisation’s default for that module.
target_output_schema Yes any (nullable)  
output_mapping_status Yes string  

V1ProjectCreateRequestRequest

The fields you can set when creating a new project via POST /projects/.

name is required; everything else is optional and falls back to a server-side default. The full project representation (including server-assigned fields such as id and created_at) is returned in the response.

Name Required Type Description
name Yes string Human-readable name shown in the UI and in lists.
description No string Short description of what the project covers.
reference_date No string (date) (nullable) Reference date used by agents that need a “today” anchor (e.g. relative date extractions). Defaults to the date the project was created.
per_document_mode No boolean When true, extraction results are scoped per-document rather than aggregated across the project. Used for projects where each document represents a separate subject (e.g. one contract per file).
per_tag_mode No boolean When true, extraction results are grouped per tag value. Should not be combined with per_document_mode.