Anthropic (Independent Publisher)
Claude is a large language model (LLM) built by Anthropic. It's trained to be a helpful assistant in a conversational tone.
This connector is available in the following products and regions:
| Service | Class | Regions |
|---|---|---|
| Logic Apps | Standard | All Logic Apps regions except the following: - Azure Government regions - Azure China regions - US Department of Defense (DoD) |
| Power Automate | Premium | All Power Automate regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
| Power Apps | Premium | All Power Apps regions except the following: - US Government (GCC) - US Government (GCC High) - China Cloud operated by 21Vianet - US Department of Defense (DoD) |
| Contact | |
|---|---|
| Name | Troy Taylor |
| URL | https://www.hitachisolutions.com |
| [email protected] |
| Connector Metadata | |
|---|---|
| Publisher | Troy Taylor |
| Website | https://www.anthropic.com/ |
| Privacy policy | https://console.anthropic.com/legal/privacy |
| Categories | AI |
Anthropic
Claude is a large language model (LLM) built by Anthropic. It's trained to be a helpful assistant in a conversational tone.
Publisher: Troy Taylor, Hitachi Solutions
Prerequisites
You will need to request access to Claude on the Claude product page.
Obtaining Credentials
You can create an API Key on the Keys page.
Supported Operations
Create a text completion
Send a prompt to Claude for completion.
Create a message
Send a prompt to Claude for message.
Known Issues and Limitations
There are no known issues at this time.
Creating a connection
The connector supports the following authentication types:
| Default | Parameters for creating connection. | All regions | Not shareable |
Default
Applicable: All regions
Parameters for creating connection.
This is not shareable connection. If the power app is shared with another user, another user will be prompted to create new connection explicitly.
| Name | Type | Description | Required |
|---|---|---|---|
| API Key | securestring | The API Key for this api | True |
Throttling Limits
| Name | Calls | Renewal Period |
|---|---|---|
| API calls per connection | 100 | 60 seconds |
Actions
| Create a message |
Send a prompt to Claude to return a message. |
| Create a text completion [DEPRECATED] |
Send a prompt to Claude for completion. |
Create a message
Send a prompt to Claude to return a message.
Parameters
| Name | Key | Required | Type | Description |
|---|---|---|---|---|
|
Model
|
model | True | string |
The model that will complete your prompt. |
|
Role
|
role | True | string |
The role. |
|
Content
|
content | True | string |
The conversation content. |
|
Max Tokens
|
max_tokens | True | integer |
The maximum number of tokens to generate before stopping. |
|
Stop Sequences
|
stop_sequences | array of string |
Custom text sequences that will cause the model to stop generating. |
|
|
System Prompt
|
system | string |
The system prompt. |
|
|
Temperature
|
temperature | double |
Amount of randomness injected into the response. |
|
|
Name
|
name | string |
The tool name. |
|
|
Description
|
description | string |
The description of the tool. |
|
|
Top K
|
top_k | integer |
Only sample from the top K options for each subsequent token. |
|
|
Top P
|
top_p | float |
Use nucleus sampling. |
Returns
| Name | Path | Type | Description |
|---|---|---|---|
|
completion
|
completion | string | |
|
id
|
id | string | |
|
model
|
model | string | |
|
stop_reason
|
stop_reason | string | |
|
type
|
type | string |
Create a text completion [DEPRECATED]
Send a prompt to Claude for completion.
Parameters
| Name | Key | Required | Type | Description |
|---|---|---|---|---|
|
Prompt
|
prompt | True | string |
The prompt you want Claude to complete. |
|
Model
|
model | string |
The version of Claude answering your request. |
|
|
Max Tokens To Sample
|
max_tokens_to_sample | True | integer |
A maximum number of tokens to generate before stopping. |
|
Stop Sequences
|
stop_sequences | array of string |
A list of strings upon which to stop generating. You probably want [" Human:"], as that's the cue for the next turn in the dialog agent. |
|
|
Stream
|
stream | boolean |
Whether to incrementally stream the response using SSE. |
|
|
Temperature
|
temperature | float |
Amount of randomness injected into the response. Ranges from 0 to 1. Use temp closer to 0 for analytical / multiple choice, and temp closer to 1 for creative and generative tasks. |
|
|
Top K
|
top_k | integer |
Only sample from the top K options for each subsequent token. |
|
|
Top P
|
top_p | float |
Does nucleus sampling, in which we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by top_p. |
Returns
| Name | Path | Type | Description |
|---|---|---|---|
|
Completion
|
completion | string |
The completion. |
|
Stop
|
stop | string |
The stop. |
|
Stop Reason
|
stop_reason | string |
The stop reason. |
|
Truncated
|
truncated | boolean |
Whether truncated. |
|
Log ID
|
log_id | string |
The log identifier. |
|
Model
|
model | string |
The model. |
|
Exception
|
exception | string |
The exception. |