> For the complete documentation index, see [llms.txt](https://docs.slier.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.slier.ai/api-reference/chat.md).
# Chat
## The chat completion object
Represents a chat completion response returned by model, based on the provided input.
* Name`id`TypestringDescription
A unique identifier for the chat completion.
* Name`object`TypestringDescription
The object type, which is always `chat.completion`.
* Name`created`TypestringDescription
A unix timestamp of when the chat completion was created.
* Name`model`TypestringDescription
The model used for the chat completion.
* Name`choices`TypearrayDescription
A list of chat completion choices. Can be more than one if `n` is greater than 1.
* Name`choices[].index`TypeintegerDescription
The index of the choice in the list of choices.
* Name`choices[].message`TypeobjectDescription
A chat completion message generated by the model.
* Name`choices[].message.role`TypestringDescription
The role of the author of this message.
* Name`choices[].message.content`Typestring or nullDescription
The contents of the message.
* Name`choices[].finish_reason`TypestringDescription
The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached.
* Name`usage`TypeobjectDescription
Usage statistics for the completion request.
* Name`usage.prompt_tokens`TypeintegerDescription
Number of tokens in the prompt.
* Name`usage.completion_tokens`TypeintegerDescription
Number of tokens in the generated completion.
* Name`usage.total_tokens`TypeintegerDescription
Total number of tokens used in the request (prompt + completion).
#### The chat completion object
```json
{
"id": "9f6280c9e7e340edb043a1b1d512ea4b",
"object": "chat.completion",
"created": 1692154125,
"model": "claude-2",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": " I'm doing well, thanks for asking!"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 9,
"total_tokens": 21
}
}
```
***
### The chat completion chunk object
Represents a streamed chunk of a chat completion response returned by model, based on the provided input.
* Name`id`TypestringDescription
A unique identifier for the chat completion.
* Name`object`TypestringDescription
The object type, which is always `chat.completion`.
* Name`created`TypestringDescription
A unix timestamp of when the chat completion was created.
* Name`model`TypestringDescription
The model used for the chat completion.
* Name`choices`TypearrayDescription
A list of chat completion choices. Can be more than one if `n` is greater than 1.
* Name`choices[].index`TypeintegerDescription
The index of the choice in the list of choices.
* Name`choices[].delta`TypeobjectDescription
A chat completion delta generated by streamed model responses.
* Name`choices[].delta.role`TypestringDescription
The role of the author of this message.
* Name`choices[].delta.content`Typestring or nullDescription
The contents of the chunk message.
* Name`choices[].finish_reason`Typestring or nullDescription
The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached.
* Name`usage`TypeobjectDescription
Usage statistics for the completion request.
* Name`usage.prompt_tokens`TypeintegerDescription
Number of tokens in the prompt.
* Name`usage.completion_tokens`TypeintegerDescription
Number of tokens in the generated completion.
* Name`usage.total_tokens`TypeintegerDescription
Total number of tokens used in the request (prompt + completion).
#### The chat completion chunk object
```json
{
"id": "9f6280c9e7e340edb043a1b1d512ea4b",
"object": "chat.completion.chunk",
"created": 1692154202,
"model": "claude-2",
"choices": [
{
"index": 0,
"delta": {
"role": "assistant",
"content": " I"
},
"finish_reason": null
}
]
}
......
{
"id": "9f6280c9e7e340edb043a1b1d512ea4b",
"object": "chat.completion.chunk",
"created": 1692154202,
"model": "claude-2",
"choices": [
{
"index": 0,
"delta": {},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 9,
"total_tokens": 21
}
}
[DONE]
```
***
### [Create chat completion](https://docs.theb.ai/chat#create-chat-completion)
Creates a model response for the given chat conversation.
**POST **
**POST **
**Available parameters**
`model` string Required ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API.
`messages` array Required A list of messages comprising the conversation so far.
* `role` string Required
* The role of the messages author. One of `system`, `user` or `assistant`.
* `content` string Required
* The contents of the message. `content` is required for all messages.
`stream` boolean or null Optional Defaults to false If set, partial message deltas will be sent. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message.
`model_params` object Optional Each model is different Used to set various parameters of the model.
* `temperature` number or null Optional
* Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
* `top_p` number or null Optional
* An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top\_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\n\nWe generally recommend altering this or `temperature` but not both.
* Obtain the other configurable parameters from the model interface.
NO STREAMINGSTREAMING
#### Example Request
POST/v1/chat/completions
```python
import requests
import json
url = "https://api.Slier.ai/v1/chat/completions"
# url = "https://api.Slier.ai/v2/chat/completions"
payload = json.dumps({
"model": "claude-2",
"messages": [
{
"role": "user",
"content": "How are you?"
}
],
"stream": false,
"model_params": {
"temperature": 1
}
})
headers = {
'Authorization': 'Bearer $API_KEY',
'Content-Type': 'application/json'
}
response = requests.request("POST", url, headers=headers, data=payload)
print(response.json())
```
#### The chat completion object
```json
{
"id": "9f6280c9e7e340edb043a1b1d512ea4b",
"object": "chat.completion",
"created": 1692154125,
"model": "claude-2",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": " I'm doing well, thanks for asking!"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 12,
"completion_tokens": 9,
"total_tokens": 21
}
}
```
#### Contents Filtered
```json
{
"error": {
"message": "This content may violate our content policy, please check https://Slier.ai/terms to learn more. If you believe this to be in error, please contact us at safety@Slier.ai to keep our systems safe and available.",
"param": "prompt",
"reason": "content_filter",
"status": 400
}
}
```
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.slier.ai/api-reference/chat.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.