MistralAI
Open, efficient, helpful and trustworthy AI models through ground-breaking innovations.
Categories: Artificial Intelligence
Type: mistral/v1
Connections
Version: 1
Bearer Token
Properties
Name | Label | Type | Description | Required |
---|---|---|---|---|
token | Token | STRING | true |
Actions
Ask
Name: ask
Ask anything you want.
Properties
Name | Label | Type | Description | Required |
---|---|---|---|---|
model | Model | STRING Optionscodestral-latest, ministral-3b-latest, ministral-8b-latest, mistral-large-latest, mistral-small-latest, open-codestral-mamba, open-mistral-nemo, pixtral-12b-2409, pixtral-large-latest | ID of the model to use. | true |
messages | Messages | ARRAY Items[{STRING(role), STRING(content), [FILE_ENTRY](attachments)}] | A list of messages comprising the conversation so far. | true |
response | Response | OBJECT Properties{STRING(responseFormat), STRING(responseSchema)} | The response from the API. | false |
maxTokens | Max Tokens | INTEGER | The maximum number of tokens to generate in the chat completion. | null |
temperature | Temperature | NUMBER | Controls randomness: Higher values will make the output more random, while lower values like will make it more focused and deterministic. | null |
topP | Top P | NUMBER | 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. | null |
stop | Stop | ARRAY Items[STRING] | Up to 4 sequences where the API will stop generating further tokens. | null |
seed | Seed | INTEGER | Keeping the same seed would output the same response. | null |
safePrompt | Safe prompt | BOOLEAN Optionstrue, false | Should the prompt be safe for work? | null |
Example JSON Structure
{ "label" : "Ask", "name" : "ask", "parameters" : { "model" : "", "messages" : [ { "role" : "", "content" : "", "attachments" : [ { "extension" : "", "mimeType" : "", "name" : "", "url" : "" } ] } ], "response" : { "responseFormat" : "", "responseSchema" : "" }, "maxTokens" : 1, "temperature" : 0.0, "topP" : 0.0, "stop" : [ "" ], "seed" : 1, "safePrompt" : false }, "type" : "mistral/v1/ask"}
Output
The output for this action is dynamic and may vary depending on the input parameters. To determine the exact structure of the output, you need to execute the action.
Document OCR
Name: ocr
Extracts text and structured content from documents.
Properties
Name | Label | Type | Description | Required |
---|---|---|---|---|
model | Model | STRING | Model to use. | true |
type | Type | STRING Optionsimage_url, document_url | Type of the document to run OCR on. | true |
url | Image URL | STRING | Url of the image to run OCR on. | true |
url | Document URL | STRING | Url of the document to run OCR on. | true |
Example JSON Structure
{ "label" : "Document OCR", "name" : "ocr", "parameters" : { "model" : "", "type" : "", "url" : "" }, "type" : "mistral/v1/ocr"}
Output
Type: OBJECT
Properties
Name | Type | Description |
---|---|---|
pages | ARRAY Items[{INTEGER(index), STRING(markdown), [{STRING(id), INTEGER(top_left_x), INTEGER(top_left_y), INTEGER(bottom_right_x), INTEGER(bottom_right_y)}](images), {INTEGER(dpi), INTEGER(height), INTEGER(width)}(dimensions)}] | |
model | STRING | |
usage_info | OBJECT Properties{INTEGER(pages_processed), INTEGER(doc_size_bytes)} |
Output Example
{ "pages" : [ { "index" : 1, "markdown" : "", "images" : [ { "id" : "", "top_left_x" : 1, "top_left_y" : 1, "bottom_right_x" : 1, "bottom_right_y" : 1 } ], "dimensions" : { "dpi" : 1, "height" : 1, "width" : 1 } } ], "model" : "", "usage_info" : { "pages_processed" : 1, "doc_size_bytes" : 1 }}