Create Chat Completion

Given a list of messages comprising a conversation, the model will return a response.

Body

model · string

The model used to generate the response. gpt-4o-mini. Default is gpt-4o-mini.

messages · array · required

A list of messages

Hide Messages object

role · string · required

The role of the messages author. One of assistant or user

content · string · required

The contents of the message. content is required for all messages, and may be null for assistant messages with function calls.

files · array

A list of file URLs to ask questions. All URLs must be publicly accessible. We currently support csv, json, xlsx, txt, html, xml, parquet, dta, sas, sav.

If you want a file supporting, get in touch at [e-mail]

Hide Toggle object

A list of file urls.

Example: ["https://data.set/titanic.csv"]

Response

Response will be sent as data-only server-sent events as they become available.

Example: Hey, how can I help?

Example Request

curl --no-buffer \
    -X POST \
    -H 'accept: text/event-stream' \
    -H 'Content-Type: application/json' \
    -H 'Authorization: Bearer <token>' \
    -d '{
        "model": "gpt-4o-mini",
        "messages": [
            {
                "role": "user",
                "content": "whats your name"
            },
            {
                "role": "assistant",
                "content": "bob"
            },
            {
                "role": "user",
                "content": "show me some interesting visuals about this data. but start with what q i asked first"
            }
        ],
        "files": [
            "https://raw.githubusercontent.com/datasciencedojo/datasets/master/titanic.csv"
        ]
    }' \
    'https://www.chatcsv.co/api/v1/chat'

Response

How may I help you today?