Chat (Long-term Memory)

POST

/chat/completions

To add long-term memory functionality to any large model, simply include a userid parameter.
If this userid appears for the first time, the backend will automatically generate a corresponding user and summarize the conversation through the LLM, extracting relevant information as long-term memory.
If this userid has appeared before, the backend will automatically retrieve the corresponding long-term memory and update the latest memory, automatically adding it to the system and passing it to the large model.
This feature supports the majority of models, requiring only that they support passing system prompts.
Note: The userid must comply with the uuidV4 standard; if it does not, the memory operation will not be executed. UUID generation test link: https://www.uuidgenerator.net/version4

This feature is supported by our partner Memobase: https://www.memobase.io/

Price:-time free, only model invocation fees are charged

Request

Header Params

Content-Type

string

required

Example:

application/json

string

required

Example:

application/json

Authorization

string

required

Enter the API key generated in the Management Backend - API KEYS into the Bearer, for example Bearer sk-xxxx

Example:

Bearer {{YOUR_API_KEY}}

Body Params application/json

model

string

required

The ID of the model to be used. For more details on which models are compatible with the Chat API, refer to the model endpoint compatibility table. (https://platform.openai.com/docs/models/model-endpoint-compatibility)

userid

string

required

a UUIDv4-formatted user ID

messages

array [object {2}]

required

Generate a chat completion message in chat format.

role

string

optional

content

string

optional

temperature

integer

optional

What sampling temperature to use, between 0 and 2. A higher value (like 0.8) will make the output more random, while a lower value (like 0.2) will make the output more focused and deterministic. We generally recommend changing this or top_p but not both.

top_p

integer

optional

An alternative to temperature sampling, called kernel sampling, where the model considers the results of markers with top_p probability mass. So 0.1 means only the tokens that make up the top 10% of probability mass are considered. We generally recommend changing this or temperature but not both.

integer

optional

How many chat completion options are generated for each input message.

stream

boolean

optional

If set, partial message deltas will be sent, just like in ChatGPT. When the token is available, the token will be sent as plain data :[DONE]`Sent, stream terminated by message. For example code, see the OpenAI Cookbook.

stop

string

optional

The API will stop generating sequences of up to 4 more tokens.

max_tokens

integer

optional

The maximum number of tokens generated when the chat is completed. The total length of input tokens and generated tokens is limited by the length of the model context.

presence_penalty

number

optional

A number between -2.0 and 2.0. Positive values penalize new tokens based on whether they have appeared in the text so far, thus increasing the likelihood that the model is talking about new topics. See more information on frequency and presence penalties.

frequency_penalty

number

optional

-2.0 and 2.0. Positive values penalize the existing frequency of a token in the text, reducing the model's likelihood of repeating the same line verbatim. See more information on frequency and presence penalties.

logit_bias

null

optional

Modifies the likelihood of a specified token appearing in the completion.Accepts a JSON object that maps tokens (specified by token IDs in the tokenizer) to associated bias values ranging from -100 to 100.Mathematically, the bias is added to the model-generated logits before sampling.The exact effect varies by model, but values between -1 and 1 should reduce or increase the likelihood of selection; values like -100 or 100 should lead to the prohibition or exclusive selection of the corresponding token.

Example

{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": "我是谁？"
    }
  ],
  "userid": "fe657e7e-862e-4be0-990d-37428979a38c"
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "gpt-4o-mini",
  "messages": [{"role": "user", "content": "我是谁？"}],
  "userid":"fe657e7e-862e-4be0-990d-37428979a38c"
}'

Responses

🟢200OK

application/json

Body

string

required

object

string

required

created

integer

required

choices

array [object {3}]

required

index

integer

optional

message

object

optional

finish_reason

string

optional

usage

object

required

prompt_tokens

integer

required

completion_tokens

integer

required

total_tokens

integer

required

Example

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\n\nHello there, how may I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Delete User Profile (Delete Memory)

Chat (Simplified API)