Skip to content

README.md

Latest commit

 

History

History
192 lines (125 loc) · 14.6 KB

README.md

File metadata and controls

192 lines (125 loc) · 14.6 KB
Raw

Agents

Overview

Available Operations

search

Search agents available to the authenticated user by agent name.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN", ""),
) as glean:

    res = glean.agents.search(name="HR Policy Agent")

    # Handle response
    print(res)

Parameters

Parameter Type Required Description Example
name Optional[str] ➖ Case-insensitive substring to match against agent names. If omitted or empty, no name filter is applied. HR Policy Agent
retries Optional[utils.RetryConfig] ➖ Configuration to override the default retry behavior of the client.

Response

models.PlatformAgentsSearchResponse

Errors

Error Type Status Code Content Type
errors.PlatformProblemDetailError 400, 401, 403, 404, 408, 413, 429 application/problem+json
errors.PlatformProblemDetailError 500, 503 application/problem+json
errors.GleanError 4XX, 5XX */*

get

Retrieve details for an agent available to the authenticated user.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN", ""),
) as glean:

    res = glean.agents.get(agent_id="<id>")

    # Handle response
    print(res)

Parameters

Parameter Type Required Description
agent_id str ✔️ ID of the agent to retrieve.
retries Optional[utils.RetryConfig] ➖ Configuration to override the default retry behavior of the client.

Response

models.PlatformAgentGetResponse

Errors

Error Type Status Code Content Type
errors.PlatformProblemDetailError 400, 401, 403, 404, 408, 429 application/problem+json
errors.PlatformProblemDetailError 500, 503 application/problem+json
errors.GleanError 4XX, 5XX */*

get_schemas

Retrieve an agent's input and output JSON schemas.

Example Usage

from glean.api_client import Glean
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN", ""),
) as glean:

    res = glean.agents.get_schemas(agent_id="<id>", include_tools=False)

    # Handle response
    print(res)

Parameters

Parameter Type Required Description
agent_id str ✔️ ID of the agent whose schemas should be retrieved.
include_tools Optional[bool] ➖ Whether to include tool metadata in the response.
retries Optional[utils.RetryConfig] ➖ Configuration to override the default retry behavior of the client.

Response

models.PlatformAgentSchemasResponse

Errors

Error Type Status Code Content Type
errors.PlatformProblemDetailError 400, 401, 403, 404, 408, 429 application/problem+json
errors.PlatformProblemDetailError 500, 503 application/problem+json
errors.GleanError 4XX, 5XX */*

create_run

Execute an agent run. Set stream to true to receive server-sent events; otherwise the response contains the final agent messages.

Example Usage

from glean.api_client import Glean, models
import os


with Glean(
    api_token=os.getenv("GLEAN_API_TOKEN", ""),
) as glean:

    res = glean.agents.create_run(agent_id="<id>", messages=[
        {
            "role": models.PlatformMessageRole.USER,
            "content": [],
        },
    ], stream=False)

    # Handle response
    print(res)

Parameters

Parameter Type Required Description
agent_id str ✔️ ID of the agent to run.
input Dict[str, Any] ➖ Input fields for an input-form triggered agent.
messages List[models.PlatformMessage] ➖ Messages to pass to the agent. When provided, the array MUST contain at least one message and each message MUST specify a valid role and non-empty content.
metadata Dict[str, Any] ➖ Metadata to pass to the agent.
stream Optional[bool] ➖ Whether to stream the run response as server-sent events.
retries Optional[utils.RetryConfig] ➖ Configuration to override the default retry behavior of the client.

Response

models.PlatformAgentsCreateRunResponse

Errors

Error Type Status Code Content Type
errors.PlatformProblemDetailError 400, 401, 403, 404, 408, 409, 413, 429 application/problem+json
errors.PlatformProblemDetailError 500, 503 application/problem+json
errors.GleanError 4XX, 5XX */*