...
Answer to the question based on the image and conversation history.
Configuration settings (technical)
...
Settings (technical)
Reference in Code
ImageUpload
Configuration
Global structure of config
Parameter | Description |
|---|---|
| used GPT model Default: |
| Instance of service |
| List of supported image extensions. Default:
|
chatHistory
Parameter | Description |
|---|---|
| Whether to use full conversation history. If False, attempt to use conversation summary from tool call. Default: |
| Max history messages to consider Default: |
| Whether to use model token limit or not Default: |
| Default token limit if model token limit is not available. Default: |
| Upper limit of tokens to keep from history. Default: |
Example Json
| Code Block | ||
|---|---|---|
| ||
{
"typeImageUploadConfig": "function",{
"functionchatHistory": {
"nameenabled": "ImageUpload"true,
"parametersmaxMessages": 10
{ },
"typelanguageModel": "object",
AZURE_GPT_4o_2024_0513"
}
} |
Template Json Config (for developers)
| Code Block | ||
|---|---|---|
| ||
{ "ImageUploadConfig": { "requiredsupportedExtensions" : [ "query.jpg", "conversation_history.jpe", ]".jpeg", "properties.png":, { ".gif", "query": { ".bmp" ], "typechatHistory": "string", { "enabled": true, "descriptionmaxMessages": "Smart10, query based on the user request but augmented with the context of conversation if needed." "useModelTokenLimit": true, "defaultTokenLimit": 4096, "percentageOfMaxTokens": 0.5 }, }, "languageModel": "image_name": { AZURE_GPT_4o_2024_0513" } } |
(Tool) Definition
| Code Block | ||
|---|---|---|
| ||
{ "type": "stringfunction", "function": { "descriptionname": "ImageUpload"Name, of the image file to be analyzed [Optional]." "parameters": { }, "type": "object", "conversation_historyrequired": { [ "typequery": "string", "descriptionconversation_history": "Summary of the history of the conversation to provide], context for the query." "properties": { } } "query": { }, "descriptiontype": "string"This, tool is designed to analyze, extract, and summarize information from images. It should be invoked whenever "description": "Smart query based on the user inquiresrequest aboutbut images."augmented with the context of } } |
Global structure of config
...
Parameter
...
Description
...
languageModel: string
...
used GPT model
Default: AZURE_GPT_4_32K_0613
...
chatHistory
...
Instance of service
...
supportedExtensions: list[string]
...
List of supported image extensions.
Default:
[".jpg",".jpe",".jpeg",".png",".gif",".bmp"]
chatHistory
...
Parameter
...
Description
...
enabled: bool
...
Whether to use full conversation history. If False, attempt to use conversation summary from tool call.
Default: true
...
maxMessages: integer
...
Max history messages to consider
Default: 10
...
useModelTokenLimit: bool
...
Whether to use model token limit or not
Default: true
...
defaultTokenLimit: integer
...
Default token limit if model token limit is not available.
Default: 4096
...
percentageOfMaxTokens: float
...
Upper limit of tokens to keep from history.
Default: 0.5
Example Json Config
| Code Block | ||
|---|---|---|
| ||
{ "ImageUploadConfig": {conversation if needed." "chatHistory": { }, "enabled": true, "maxMessagesimage_name": { 10 }, "languageModeltype": "AZURE_GPT_4o_2024_0513"string", } } |
Template Json Config (for developers)
| Code Block | ||
|---|---|---|
| ||
{ "ImageUploadConfig": { "supportedExtensionsdescription" : ["Name of the image file to be analyzed "[Optional].jpg", ".jpe",}, ".jpeg",conversation_history": { ".pngtype": "string", "description".gif: ",Summary of the history of the conversation to ".bmpprovide context for the query." ], "chatHistory": {} "enabled": true, } "maxMessages": 10}, "useModelTokenLimitdescription": true,"This tool is designed to "defaultTokenLimit": 4096analyze, extract, and summarize information "percentageOfMaxTokens": 0.5 }, "languageModel": "AZURE_GPT_4o_2024_0513"from images. It should be invoked whenever the user inquires about images." } } |
...
Author |
|---|