La spec OpenAPI
Home
Public Preview
Tree BG 1
Tree
Tree
TreeLeaves
TreeLeaves
Cat IdleGrassGrassRockRock

Jeux de données d'observabilité bêta

Lister les jeux de données existants

GET /v1/observability/datasets

200

Réponse réussie

datasets
*PaginatedResultDatasetPreview

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.list(page_size=50, page=1)

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets \
 -X GET \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE'

200

{
  "datasets": {
    "count": 87
  }
}

Créer un nouveau jeu de données vide

POST /v1/observability/datasets

201

Réponse réussie

created_at
*date-time
deleted_at
*date-time|null
description
*string
id
*string
name
*string
owner_id
*string
updated_at
*date-time
workspace_id
*string

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.create(name="<value>", description="citizen whoever sustenance necessary vibrant openly")

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets \
 -X POST \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE' \
 -H 'Content-Type: application/json' \
 -d '{
  "description": "My Dataset description",
  "name": "My Dataset"
}'

201

{
  "created_at": "2025-12-17T10:25:07.818693Z",
  "deleted_at": null,
  "description": "My resource description.",
  "id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "name": "My resource",
  "owner_id": "9c0ab39f-0cd0-46cd-bd30-8bf2d50be5ce",
  "updated_at": "2025-12-17T10:41:03.469341Z",
  "workspace_id": "019b2bd7-96e7-7219-8c0b-45a73da50088"
}

Obtenir un jeu de données par identifiant

GET /v1/observability/datasets/{dataset_id}

200

Réponse réussie

created_at
*date-time
deleted_at
*date-time|null
description
*string
id
*string
name
*string
owner_id
*string
updated_at
*date-time
workspace_id
*string

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.fetch(dataset_id="036fa362-e080-4fa5-beff-a334a70efb58")

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id} \
 -X GET \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE'

200

{
  "created_at": "2025-12-17T10:25:07.818693Z",
  "deleted_at": null,
  "description": "My resource description.",
  "id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "name": "My resource",
  "owner_id": "9c0ab39f-0cd0-46cd-bd30-8bf2d50be5ce",
  "updated_at": "2025-12-17T10:41:03.469341Z",
  "workspace_id": "019b2bd7-96e7-7219-8c0b-45a73da50088"
}

Supprimer un jeu de données

DELETE /v1/observability/datasets/{dataset_id}

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    mistral.beta.observability.datasets.delete(dataset_id="baf961a3-bb8e-4085-89ef-de9c5d8c4e77")

    # Use the SDK ...


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id} \
 -X DELETE \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE' \
 -H 'Content-Type: application/json'

Modifier partiellement un jeu de données

PATCH /v1/observability/datasets/{dataset_id}

200

Réponse réussie

created_at
*date-time
deleted_at
*date-time|null
description
*string
id
*string
name
*string
owner_id
*string
updated_at
*date-time
workspace_id
*string

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.update(dataset_id="95be9afc-fc05-44a6-af9f-2362de1224f9")

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id} \
 -X PATCH \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE' \
 -H 'Content-Type: application/json' \
 -d '{}'

200

{
  "created_at": "2025-12-17T10:25:07.818693Z",
  "deleted_at": null,
  "description": "My resource description.",
  "id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "name": "My resource",
  "owner_id": "9c0ab39f-0cd0-46cd-bd30-8bf2d50be5ce",
  "updated_at": "2025-12-17T10:41:03.469341Z",
  "workspace_id": "019b2bd7-96e7-7219-8c0b-45a73da50088"
}

Lister les enregistrements existants dans le jeu de données

GET /v1/observability/datasets/{dataset_id}/records

200

Réponse réussie

records
*PaginatedResultDatasetRecord

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.list_records(dataset_id="444d2a88-e636-4bc0-ab6c-919bedaed112", page_size=50, page=1)

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id}/records \
 -X GET \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE'

200

{
  "records": {
    "count": 87
  }
}

Ajouter une conversation au jeu de données

POST /v1/observability/datasets/{dataset_id}/records

201

Réponse réussie

created_at
*date-time
dataset_id
*string
deleted_at
*date-time|null
id
*string
payload
*ConversationPayload
properties
*map<any>
source
*"EXPLORER"|"UPLOADED_FILE"|"DIRECT_INPUT"|"PLAYGROUND"
updated_at
*date-time

Playground

Testez les endpoints en direct

from mistralai.client import Mistral, models
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.create_record(dataset_id="4c54ed13-1459-44e1-8696-1a6df06f7177", payload=models.ConversationPayload(
        messages=[
            {
                "key": "<value>",
            },
            {
                "key": "<value>",
                "key1": "<value>",
            },
        ],
    ), properties={
        "key": "<value>",
        "key1": "<value>",
        "key2": "<value>",
    })

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id}/records \
 -X POST \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE' \
 -H 'Content-Type: application/json' \
 -d '{
  "payload": {
    "messages": [
      [
        null
      ]
    ]
  },
  "properties": [
    null
  ]
}'

201

{
  "created_at": "2025-12-17T10:25:07.818693Z",
  "dataset_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "deleted_at": null,
  "id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "payload": {
    "messages": [
      [
        null
      ]
    ]
  },
  "properties": [
    null
  ],
  "source": "EXPLORER",
  "updated_at": "2025-12-17T10:41:03.469341Z"
}

Peupler le jeu de données avec une campagne

POST /v1/observability/datasets/{dataset_id}/imports/from-campaign

202

Réponse réussie

created_at
*date-time
creator_id
*string
dataset_id
*string
deleted_at
*date-time|null
id
*string
message
string|null
progress
integer|null
status
*"RUNNING"|"COMPLETED"|"FAILED"|"CANCELED"|"TERMINATED"|"CONTINUED_AS_NEW"|"TIMED_OUT"|"UNKNOWN"
updated_at
*date-time
workspace_id
*string

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.import_from_campaign(dataset_id="306b5f31-e31c-4e06-9220-e3008c61bf1b", campaign_id="71a2e42d-7414-4fe6-89cb-44a2122b6f6b")

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id}/imports/from-campaign \
 -X POST \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE' \
 -H 'Content-Type: application/json' \
 -d '{
  "campaign_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}'

202

{
  "created_at": "2025-12-17T10:25:07.818693Z",
  "creator_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "dataset_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "deleted_at": null,
  "id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "status": "RUNNING",
  "updated_at": "2025-12-17T10:41:03.469341Z",
  "workspace_id": "019b2bd7-96e7-7219-8c0b-45a73da50088"
}

Peupler le jeu de données avec des échantillons provenant de l'explorateur

POST /v1/observability/datasets/{dataset_id}/imports/from-explorer

202

Réponse réussie

created_at
*date-time
creator_id
*string
dataset_id
*string
deleted_at
*date-time|null
id
*string
message
string|null
progress
integer|null
status
*"RUNNING"|"COMPLETED"|"FAILED"|"CANCELED"|"TERMINATED"|"CONTINUED_AS_NEW"|"TIMED_OUT"|"UNKNOWN"
updated_at
*date-time
workspace_id
*string

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.import_from_explorer(dataset_id="ee1930e9-54f7-4c68-aa8a-40fe5d2a3485", completion_event_ids=[
        "<value 1>",
        "<value 2>",
        "<value 3>",
    ])

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id}/imports/from-explorer \
 -X POST \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE' \
 -H 'Content-Type: application/json' \
 -d '{
  "completion_event_ids": [
    "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
  ]
}'

202

{
  "created_at": "2025-12-17T10:25:07.818693Z",
  "creator_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "dataset_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "deleted_at": null,
  "id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "status": "RUNNING",
  "updated_at": "2025-12-17T10:41:03.469341Z",
  "workspace_id": "019b2bd7-96e7-7219-8c0b-45a73da50088"
}

Peupler le jeu de données avec des échantillons provenant d'un fichier téléchargé

POST /v1/observability/datasets/{dataset_id}/imports/from-file

202

Réponse réussie

created_at
*date-time
creator_id
*string
dataset_id
*string
deleted_at
*date-time|null
id
*string
message
string|null
progress
integer|null
status
*"RUNNING"|"COMPLETED"|"FAILED"|"CANCELED"|"TERMINATED"|"CONTINUED_AS_NEW"|"TIMED_OUT"|"UNKNOWN"
updated_at
*date-time
workspace_id
*string

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.import_from_file(dataset_id="1c96c925-cc58-4529-863d-9fe66a6f1924", file_id="<id>")

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id}/imports/from-file \
 -X POST \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE' \
 -H 'Content-Type: application/json' \
 -d '{
  "file_id": "7f8e9d0c-1b2a-3c4d-5e6f-7a8b9c0d1e2f"
}'

202

{
  "created_at": "2025-12-17T10:25:07.818693Z",
  "creator_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "dataset_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "deleted_at": null,
  "id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "status": "RUNNING",
  "updated_at": "2025-12-17T10:41:03.469341Z",
  "workspace_id": "019b2bd7-96e7-7219-8c0b-45a73da50088"
}

Peupler le jeu de données avec des échantillons provenant du terrain de jeu

POST /v1/observability/datasets/{dataset_id}/imports/from-playground

202

Réponse réussie

created_at
*date-time
creator_id
*string
dataset_id
*string
deleted_at
*date-time|null
id
*string
message
string|null
progress
integer|null
status
*"RUNNING"|"COMPLETED"|"FAILED"|"CANCELED"|"TERMINATED"|"CONTINUED_AS_NEW"|"TIMED_OUT"|"UNKNOWN"
updated_at
*date-time
workspace_id
*string

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.import_from_playground(dataset_id="5cb42584-5fcf-4837-997a-6a67c5e6900d", conversation_ids=[])

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id}/imports/from-playground \
 -X POST \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE' \
 -H 'Content-Type: application/json' \
 -d '{
  "conversation_ids": [
    "9d8c7b6a-5e4f-3210-fedc-ba9876543210"
  ]
}'

202

{
  "created_at": "2025-12-17T10:25:07.818693Z",
  "creator_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "dataset_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "deleted_at": null,
  "id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "status": "RUNNING",
  "updated_at": "2025-12-17T10:41:03.469341Z",
  "workspace_id": "019b2bd7-96e7-7219-8c0b-45a73da50088"
}

Peupler le jeu de données avec des échantillons provenant d'un autre jeu de données

POST /v1/observability/datasets/{dataset_id}/imports/from-dataset

202

Réponse réussie

created_at
*date-time
creator_id
*string
dataset_id
*string
deleted_at
*date-time|null
id
*string
message
string|null
progress
integer|null
status
*"RUNNING"|"COMPLETED"|"FAILED"|"CANCELED"|"TERMINATED"|"CONTINUED_AS_NEW"|"TIMED_OUT"|"UNKNOWN"
updated_at
*date-time
workspace_id
*string

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.import_from_dataset_records(dataset_id="ada96a08-d724-4e5c-9111-aaf1bdb7d588", dataset_record_ids=[
        "58fe798a-537b-4c61-9efc-d1d96d5d264a",
        "cfa1d197-deda-456e-906b-dd84dccfcd17",
    ])

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id}/imports/from-dataset \
 -X POST \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE' \
 -H 'Content-Type: application/json' \
 -d '{
  "dataset_record_ids": [
    "c2e8a4f0-1d3b-4a6c-8e9f-0a1b2c3d4e5f"
  ]
}'

202

{
  "created_at": "2025-12-17T10:25:07.818693Z",
  "creator_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "dataset_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "deleted_at": null,
  "id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "status": "RUNNING",
  "updated_at": "2025-12-17T10:41:03.469341Z",
  "workspace_id": "019b2bd7-96e7-7219-8c0b-45a73da50088"
}

Exporter vers l'API Fichiers et récupérer l'URL présignée pour télécharger le fichier JSONL résultant

GET /v1/observability/datasets/{dataset_id}/exports/to-jsonl

200

Réponse réussie

file_url
*string

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.export_to_jsonl(dataset_id="d521add6-d909-4a69-a460-cb880d87b773")

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id}/exports/to-jsonl \
 -X GET \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE'

200

{
  "file_url": "https://example.com/data.jsonl"
}

Obtenir l'état d'une tâche d'importation de jeu de données

GET /v1/observability/datasets/{dataset_id}/tasks/{task_id}

200

Réponse réussie

created_at
*date-time
creator_id
*string
dataset_id
*string
deleted_at
*date-time|null
id
*string
message
string|null
progress
integer|null
status
*"RUNNING"|"COMPLETED"|"FAILED"|"CANCELED"|"TERMINATED"|"CONTINUED_AS_NEW"|"TIMED_OUT"|"UNKNOWN"
updated_at
*date-time
workspace_id
*string

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.fetch_task(dataset_id="b64b504e-58a2-4d52-979b-e2634b301235", task_id="1713cde2-dea1-410d-851e-8cea964ffa14")

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id}/tasks/{task_id} \
 -X GET \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE'

200

{
  "created_at": "2025-12-17T10:25:07.818693Z",
  "creator_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "dataset_id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "deleted_at": null,
  "id": "019b2bd7-96e7-7219-8c0b-45a73da50088",
  "status": "RUNNING",
  "updated_at": "2025-12-17T10:41:03.469341Z",
  "workspace_id": "019b2bd7-96e7-7219-8c0b-45a73da50088"
}

Lister les tâches d'importation pour le jeu de données donné

GET /v1/observability/datasets/{dataset_id}/tasks

200

Réponse réussie

tasks
*PaginatedResultDatasetImportTask

Playground

Testez les endpoints en direct

from mistralai.client import Mistral
import os


with Mistral(
    api_key=os.getenv("MISTRAL_API_KEY", ""),
) as mistral:

    res = mistral.beta.observability.datasets.list_tasks(dataset_id="29903443-7f9c-42a6-9b6b-fc5cbef4191a", page_size=50, page=1)

    # Handle response
    print(res)


curl https://api.mistral.ai/v1/observability/datasets/{dataset_id}/tasks \
 -X GET \
 -H 'Authorization: Bearer YOUR_APIKEY_HERE'

200

{
  "tasks": {
    "count": 87
  }
}