Create a chatflow session

Create a new chatflow session with specified messages, model, and optional parameters. This endpoint starts a new chat session and returns the AI response based on the provided messages and configuration. You can optionally include tool configuration, workspace IDs, file IDs, and scope parameters to control the context of the conversation.

POST /api/v2/tools/chatflows

Try it

cURL

SimpleChatMessage

curl --request POST \
  --url https://paradigm.lighton.ai/api/v2/tools/chatflows/ \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "role": "user",
      "content": "Hello, what can you help me with?"
    }
  ]
}
'

200

{
  "id": 123,
  "created_at": "2023-11-07T05:31:56Z",
  "document_extracts": [
    {
      "id": 123,
      "created_at": "2023-11-07T05:31:56Z",
      "chat_response_id": 123,
      "document_id": 123,
      "page_start": 1073741823,
      "page_end": 4611686018427388000,
      "document_name": "<string>",
      "document_file_type": "<string>",
      "metadata": {},
      "document_external_url": "<string>",
      "document_datasource_name": "<string>",
      "document_workspace_name": "<string>",
      "text": "<string>"
    }
  ],
  "flag_created_at": "<string>",
  "chat_message": 123,
  "text": "<string>",
  "error_message": "<string>",
  "completion": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "is_chosen": true,
  "source": "embeddings"
}

Authorizations

Authorization · string · header · required

Bearer token authentication

Body

Request serializer for creating a chatflow.

messages · string · required

List of messages for the chatflow conversation

model · string | null

Model to use for the chatflow, must exist and be configured from the admin

tool · string | null

Tool to use for the chatflow, must exist and be configured from the admin

workspace_ids · integer[]

List of workspace IDs whose documents will be added to scope

file_ids · integer[]

List of document IDs that will be added to scope

company_scope · boolean

Include documents from company scope

private_scope · boolean

Include documents from private scope

Response

200

application/json

Successful response

id · integer · required

created_at · string<date-time> · required

document_extracts · object[] · required

Show child attributes

document_extracts. id · integer · required

document_extracts. created_at · string<date-time> · required

document_extracts. chat_response_id · integer · required

document_extracts. document_id · integer · required

document_extracts. page_start · integer · required

Required range: 0 <= x <= 2147483647

document_extracts. page_end · integer<int64> · required

Required range: 0 <= x <= 9223372036854776000

document_extracts. document_name · string · required

document_extracts. document_file_type · string · required

document_extracts. metadata · object · required

Show child attributes

document_extracts.metadata. {key} · any

document_extracts. document_external_url · string · required

document_extracts. document_datasource_name · string · required

document_extracts. document_workspace_name · string · required

document_extracts. text · string | null

flag_created_at · string | null · required

chat_message · integer | null

text · string | null

error_message · string | null

completion · string<uuid> | null

is_chosen · boolean

source · enum<string>

• embeddings - embeddings
• corpus - corpus

Available options: embeddings, corpus