agents
agents.test
conversations
data_sources
events
incidents
insights
insights.workflows
insights.tools
custom_messages
prompts
session_labels
sessions.transcript
sessions.full-summary
session_debug
channels.targets
directory
dashboards
outbound.batches
- GETList Outbound Communication Batches
- POSTCreate Outbound Communication Batch
- GETGet Outbound Communication Batch
- PUTUpdate Outbound Communication Batch
- DELDelete Outbound Communication Batch
- POSTUpload Outbound Communication Batch
- GETFetch Outbound Communication Batch Results
- POSTCreate Outbound Communication Request
- POSTDelete Requests By List Of Reference Ids
outbound.campaigns
language_groups
takeouts
Prompt List
List the existing prompts
import os
import syllable_sdk
from syllable_sdk import SyllableSDK
with SyllableSDK(
api_key_header=os.getenv("SYLLABLESDK_API_KEY_HEADER", ""),
) as ss_client:
res = ss_client.prompts.list(page=0, search_fields=[
syllable_sdk.PromptProperties.NAME,
], search_field_values=[
"Some Object Name",
], start_datetime="2023-01-01T00:00:00Z", end_datetime="2024-01-01T00:00:00Z")
# Handle response
print(res){
"items": [
{
"name": "Weather Agent Prompt",
"description": "Prompt for a weather agent.",
"type": "prompt_v1",
"context": "You are a weather agent. Answer the user's questions about weather and nothing else.",
"tools": "hangup",
"llm_config": {
"model": "gpt-4o",
"provider": "openai",
"version": "2024-08-06"
},
"id": 1,
"edit_comments": "Updated prompt text to include requirement to not answer questions that aren't about weather.",
"last_updated": "2024-01-01T12:00:00Z",
"last_updated_by": "user@email.com",
"agent_count": 5,
"tools_full": [
{
"name": "Weather Fetcher",
"definition": {
"endpoint": {
"argument_location": "query",
"method": "get",
"url": "https://api.open-meteo.com/v1/forecast"
},
"tool": {
"function": {
"description": "Get the weather for a city",
"name": "get_weather",
"parameters": {
"properties": {
"latitude": {
"description": "Latitude of the city",
"type": "number"
},
"longitude": {
"description": "Longitude of the city",
"type": "number"
},
"current": {
"default": "temperature_2m,relative_humidity_2m,precipitation,rain,showers",
"description": "Information to retrieve from the open-meteo API, comma-separated",
"type": "string"
}
},
"required": [
"latitude",
"longitude",
"current"
],
"type": "object"
}
},
"type": "function"
},
"type": "endpoint"
},
"service_id": 1,
"id": 1,
"last_updated_comments": "Updated to use new API endpoint",
"service_name": "<string>",
"prompts_info": [
{
"id": 1,
"name": "Test Prompt"
}
],
"agents_info": [
{
"id": 1,
"name": "Test Agent"
}
],
"last_updated": "2023-11-07T05:31:56Z",
"last_updated_by": "user@email.com"
}
]
}
],
"page": 0,
"page_size": 25,
"total_pages": 4,
"total_count": 100
}Authorizations
Query Parameters
The page number from which to start (0-based)
x >= 00
The maximum number of items to return
x >= 025
String names of fields to search. Correspond by index to search field values
Names of prompt fields supported for filtering/sorting on list endpoint.
id, name, description, name_description, context, tools, llm_config, last_updated, last_updated_by, agent_count "name"
Values of fields to search. Correspond by index to search fields. Unless field name contains "list", an individual search field value cannot be a list
"Some Object Name"
The field whose value should be used to order the results
id, name, description, name_description, context, tools, llm_config, last_updated, last_updated_by, agent_count "name"
The direction in which to order the results
asc, desc The fields to include in the response
Names of prompt fields supported for filtering/sorting on list endpoint.
id, name, description, name_description, context, tools, llm_config, last_updated, last_updated_by, agent_count The start datetime for filtering results
"2023-01-01T00:00:00Z"
The end datetime for filtering results
"2024-01-01T00:00:00Z"
Response
List of items returned from the query
Response model for prompt operations. A prompt defines the behavior of an agent by delivering instructions to the LLM about how the agent should behave. A prompt can be linked to one or more agents. A prompt can also be linked to tools to allow an agent using it to use those tools. For more information, see Console docs.
The prompt name
"Weather Agent Prompt"
The type of the prompt
"prompt_v1"
The configuration for the LLM that the prompt uses
Provider of the LLM model.
azure_openai, google, openai Name of the model. Must match the deployment name in Azure AI Studio.
"gpt-4o"
Optional model version.
"2024-05-13"
Version of the provider's API.
"2024-06-01"
Temperature parameter for the model. Determines randomness of responses - higher is more random, lower is more focused. Must be between 0.0 and 2.0, inclusive.
1
Controls the reproducibility of the job. The LLM will give the same or similar responses given the same inputs in multiple conversations with the same seed.
123
The internal ID of the prompt
1
The last updated date of the prompt
"2024-01-01T12:00:00Z"
The description of the prompt
"Prompt for a weather agent."
The prompt text that will be sent to the LLM at the beginning of the conversation
"You are a weather agent. Answer the user's questions about weather and nothing else."
Names of the tools to which the prompt has access (DEPRECATED - use information from full tools field instead)
"hangup"
The comments for the most recent edit to the prompt
"Updated prompt text to include requirement to not answer questions that aren't about weather."
Email address of the user who most recently updated the prompt
"user@email.com"
The number of agents using the prompt
5
Full definitions of tools to which the prompt has access
Response model for tool operations. A tool is a function that an agent can call to perform actions like accessing databases, making API calls, or processing data. For an agent to have access to a tool, the prompt associated with that agent should be linked to the tool and include instructions to use it. For more information, see Console docs.
The name of the tool
"Weather Fetcher"
The definition of the tool
The tool definition to be used by the OpenAI API.
The action to take when the LLM calls the tool.
action, endpoint, context, log "endpoint"
The configuration for an HTTP API call.
The endpoint URL of the external service to call.
"https://api.example.com"
The HTTP method to use for the service call.
get, post How to pass the arguments to the request.
body, form, path, query The default values for the parameters of the function/tool call.
Parameters for the tool whose values should be set at config time (i.e., not provided by the LLM).
A parameter for the tool whose value should be set at config time.
The name of the parameter - must be unique within the tool.
"temperature_unit"
Whether the parameter is required to have a value assigned.
true
The expected type for the parameter.
string, int, boolean, data_source_list The description of the parameter.
"Whether the temperature information should be fetched in celsius or fahrenheit."
The default value for the parameter. If type is string, must be a string. If type is int, must be an int. If type is boolean, must be a boolean. If type is data_source_list, must be a list of strings (data source names).
[
{
"default": "fahrenheit",
"description": "Whether the temperature information should be fetched in Celsius or Fahrenheit",
"name": "temperature_unit",
"required": false,
"type": "string"
}
]
The optional result of the tool call. Only used for context tools.
Internal ID of the service to which the tool belongs
1
The internal ID of the tool
1
The timestamp of the most recent update to the service
The email of the user who last updated the tool
"user@email.com"
Comments for the most recent edit to the tool.
"Updated to use new API endpoint"
The name of the service to which the tool belongs
The page number of the results (0-based)
0
The number of items returned per page
25
The total number of pages of results given the indicated page size
4
The total number of items returned from the query
100
import os
import syllable_sdk
from syllable_sdk import SyllableSDK
with SyllableSDK(
api_key_header=os.getenv("SYLLABLESDK_API_KEY_HEADER", ""),
) as ss_client:
res = ss_client.prompts.list(page=0, search_fields=[
syllable_sdk.PromptProperties.NAME,
], search_field_values=[
"Some Object Name",
], start_datetime="2023-01-01T00:00:00Z", end_datetime="2024-01-01T00:00:00Z")
# Handle response
print(res){
"items": [
{
"name": "Weather Agent Prompt",
"description": "Prompt for a weather agent.",
"type": "prompt_v1",
"context": "You are a weather agent. Answer the user's questions about weather and nothing else.",
"tools": "hangup",
"llm_config": {
"model": "gpt-4o",
"provider": "openai",
"version": "2024-08-06"
},
"id": 1,
"edit_comments": "Updated prompt text to include requirement to not answer questions that aren't about weather.",
"last_updated": "2024-01-01T12:00:00Z",
"last_updated_by": "user@email.com",
"agent_count": 5,
"tools_full": [
{
"name": "Weather Fetcher",
"definition": {
"endpoint": {
"argument_location": "query",
"method": "get",
"url": "https://api.open-meteo.com/v1/forecast"
},
"tool": {
"function": {
"description": "Get the weather for a city",
"name": "get_weather",
"parameters": {
"properties": {
"latitude": {
"description": "Latitude of the city",
"type": "number"
},
"longitude": {
"description": "Longitude of the city",
"type": "number"
},
"current": {
"default": "temperature_2m,relative_humidity_2m,precipitation,rain,showers",
"description": "Information to retrieve from the open-meteo API, comma-separated",
"type": "string"
}
},
"required": [
"latitude",
"longitude",
"current"
],
"type": "object"
}
},
"type": "function"
},
"type": "endpoint"
},
"service_id": 1,
"id": 1,
"last_updated_comments": "Updated to use new API endpoint",
"service_name": "<string>",
"prompts_info": [
{
"id": 1,
"name": "Test Prompt"
}
],
"agents_info": [
{
"id": 1,
"name": "Test Agent"
}
],
"last_updated": "2023-11-07T05:31:56Z",
"last_updated_by": "user@email.com"
}
]
}
],
"page": 0,
"page_size": 25,
"total_pages": 4,
"total_count": 100
}