AzureOpenAIChat
This module implements a wrapper for Azure OpenAI chat models, using BaseLLM as a base class.
AzureOpenAIChat
Bases: BaseChatLLM
A class for interacting with a Azure OpenAI deployment throught the OpenAI Chat API.
Inherits from BaseLLM.
Uses the specified OpenAI model and parameters for interacting with the OpenAI chat API, and provides methods to add, remove, replace messages, update system prompts, and generate responses.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
system_prompt |
str
|
The system prompt to use for the chat model. |
required |
deployment |
str
|
The deployment name of the Azure OpenAI model. |
'gpt-35-turbo'
|
azure_openai_endpoint |
str
|
The Azure OpenAI endpoint to use. |
required |
azure_api_version |
str
|
The Azure OpenAI API version to use. |
'2023-05-15'
|
temperature |
float
|
The temperature to use for text generation. |
0.7
|
max_tokens |
int
|
The maximum number of tokens to generate. |
250
|
max_retries |
int
|
The maximum number of retries for generating tokens. |
3
|
api_key |
str
|
The API key to use for interacting with the OpenAI API. |
required |
Attributes:
Name | Type | Description |
---|---|---|
temperature |
float
|
The temperature to use for text generation. |
max_tokens |
int
|
The maximum number of tokens to generate. |
max_retries |
int
|
The maximum number of retries for generating tokens. |
verbose |
bool
|
Whether to print debug information. |
Source code in llmflows/llms/azure_openai_chat.py
20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 |
|
generate(message_history)
Sends the messages to the OpenAI chat API and returns a chat message response.
Returns:
Type | Description |
---|---|
tuple[str, dict, dict]
|
A tuple containing the generated chat message, raw output data, and model configuration. |
Source code in llmflows/llms/azure_openai_chat.py
generate_async(message_history)
async
Async function that sends the messages to the OpenAI chat API and returns a chat message response.
Returns:
Type | Description |
---|---|
tuple[str, dict, dict]
|
A tuple containing the generated chat message, raw output data, and model configuration. |