POST
/
v1
/
chat
/
completions
curl --request POST \
  --url https://premai.io/v1/chat/completions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '{
  "project_id": 123,
  "session_id": "<string>",
  "repositories": {
    "ids": [
      123
    ],
    "limit": 3,
    "similarity_threshold": 0.5
  },
  "messages": [
    {
      "role": "user",
      "content": "<string>"
    }
  ],
  "model": "<string>",
  "system_prompt": "<string>",
  "frequency_penalty": 2,
  "logit_bias": {},
  "max_tokens": 1,
  "presence_penalty": 0,
  "response_format": {},
  "seed": 123,
  "stop": "<string>",
  "stream": true,
  "temperature": 1,
  "top_p": 123,
  "tools": [
    {}
  ],
  "user": "<string>"
}'
{
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "user",
        "content": "<string>"
      },
      "finish_reason": "<string>"
    }
  ],
  "created": 123,
  "model": "<string>",
  "provider_name": "<string>",
  "provider_id": "<string>",
  "document_chunks": [
    {
      "repository_id": 123,
      "document_id": 123,
      "chunk_id": 123,
      "document_name": "<string>",
      "similarity_score": 123,
      "content": "<string>"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  },
  "trace_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a"
}

Authorizations

​
Authorization
string
header
required

Body

​
project_id
integer
required

The ID of the project to use.

​
messages
object[]
required

A list of messages comprising the conversation so far.

​
session_id
string

The ID of the session to use. It helps to track the chat history.

​
repositories
object

Options for Retrieval Augmented Generation (RAG). Will override launched model settings

​
model
string

ID of the model to use. See the model endpoint compatibility table for details.

​
system_prompt
string

The system prompt to use.

​
frequency_penalty
number

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency.

Required range: 2 < x < 2
​
logit_bias
object | null

JSON object that maps tokens to an associated bias value from -100 to 100.

​
max_tokens
integer | null

The maximum number of tokens to generate in the chat completion.

Required range: x > 0
​
presence_penalty
number

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far.

Required range: -2 < x < 2
​
response_format
object | null

An object specifying the format that the model must output.

​
seed
integer | null

This feature is in Beta. If specified, our system will make a best effort to sample deterministically.

​
stop
string | null

Up to 4 sequences where the API will stop generating further tokens.

​
stream
boolean

If set, partial message deltas will be sent, like in ChatGPT.

​
temperature
number | null

What sampling temperature to use, between 0 and 2.

Required range: 0 < x < 2
​
top_p
number | null

An alternative to sampling with temperature, called nucleus sampling.

​
tools
object[]

A list of tools the model may call. Currently, only functions are supported as a tool.

​
user
string | null

A unique identifier representing your end-user.

Response

200
application/json
​
choices
object[]
required

A list of chat completion choices. Can be more than one if n is greater than 1.

​
created
integer
required

The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp.

​
model
string
required

The model to generate the completion.

​
provider_name
string
required

The name of the provider that generated the completion.

​
provider_id
string
required

The ID of the provider that generated the completion.

​
usage
object
required

The usage statistics for the completion.

​
trace_id
string
required

The trace ID of the completion.

​
document_chunks
object[]

Chunks used to improve the completion

Was this page helpful?

Post apirepositoriesrepository documentPost v1embeddings