Skip to main content

No project description provided

Project description

Letta Python Library

fern shield pypi

The Letta Python library provides convenient access to the Letta API from Python.

Installation

pip install letta-client

Reference

A full reference for this library is available here.

Usage

Instantiate and use the client with the following:

from letta_client import Letta

client = Letta(
    project="YOUR_PROJECT",
    token="YOUR_TOKEN",
)
client.tools.create(
    source_code="source_code",
)

Async Client

The SDK also exports an async client so that you can make non-blocking calls to our API.

import asyncio

from letta_client import AsyncLetta

client = AsyncLetta(
    project="YOUR_PROJECT",
    token="YOUR_TOKEN",
)


async def main() -> None:
    await client.tools.create(
        source_code="source_code",
    )


asyncio.run(main())

Exception Handling

When the API returns a non-success status code (4xx or 5xx response), a subclass of the following error will be thrown.

from letta_client.core.api_error import ApiError

try:
    client.tools.create(...)
except ApiError as e:
    print(e.status_code)
    print(e.body)

Streaming

The SDK supports streaming responses, as well, the response will be a generator that you can loop over.

from letta_client import Letta, StdioServerConfig

client = Letta(
    project="YOUR_PROJECT",
    token="YOUR_TOKEN",
)
response = client.tools.connect_mcp_server(
    request=StdioServerConfig(
        server_name="server_name",
        command="command",
        args=["args"],
    ),
)
for chunk in response.data:
    yield chunk

Advanced

Access Raw Response Data

The SDK provides access to raw response data, including headers, through the .with_raw_response property. The .with_raw_response property returns a "raw" client that can be used to access the .headers and .data attributes.

from letta_client import Letta

client = Letta(
    ...,
)
response = client.tools.with_raw_response.create(...)
print(response.headers)  # access the response headers
print(response.data)  # access the underlying object
with client.tools.with_raw_response.connect_mcp_server(...) as response:
    print(response.headers)  # access the response headers
    for chunk in response.data:
        print(chunk)  # access the underlying object(s)

Retries

The SDK is instrumented with automatic retries with exponential backoff. A request will be retried as long as the request is deemed retryable and the number of retry attempts has not grown larger than the configured retry limit (default: 2).

A request is deemed retryable when any of the following HTTP status codes is returned:

  • 408 (Timeout)
  • 429 (Too Many Requests)
  • 5XX (Internal Server Errors)

Use the max_retries request option to configure this behavior.

client.tools.create(..., request_options={
    "max_retries": 1
})

Timeouts

The SDK defaults to a 60 second timeout. You can configure this with a timeout option at the client or request level.

from letta_client import Letta

client = Letta(
    ...,
    timeout=20.0,
)


# Override timeout for a specific method
client.tools.create(..., request_options={
    "timeout_in_seconds": 1
})

Custom Client

You can override the httpx client to customize it for your use-case. Some common use-cases include support for proxies and transports.

import httpx
from letta_client import Letta

client = Letta(
    ...,
    httpx_client=httpx.Client(
        proxies="http://my.test.proxy.example.com",
        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
    ),
)

Contributing

While we value open-source contributions to this SDK, this library is generated programmatically. Additions made directly to this library would have to be moved over to our generation code, otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept, but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!

On the other hand, contributions to the README are always very welcome!

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

letta_client-0.1.237.tar.gz (162.0 kB view details)

Uploaded Source

Built Distribution

letta_client-0.1.237-py3-none-any.whl (405.8 kB view details)

Uploaded Python 3

File details

Details for the file letta_client-0.1.237.tar.gz.

File metadata

  • Download URL: letta_client-0.1.237.tar.gz
  • Upload date:
  • Size: 162.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.8.18 Linux/6.11.0-1018-azure

File hashes

Hashes for letta_client-0.1.237.tar.gz
Algorithm Hash digest
SHA256 082173c27fc72fa3be17bd0e10b06b22d5eae03cf7f78675ce460357c0e7b0ff
MD5 46d40039593a9991a9df8f158e6b84b8
BLAKE2b-256 0d866fe73a686eaeaf7ec733709fe1c43d9bef0e1b4962695594492a6219e9cf

See more details on using hashes here.

File details

Details for the file letta_client-0.1.237-py3-none-any.whl.

File metadata

  • Download URL: letta_client-0.1.237-py3-none-any.whl
  • Upload date:
  • Size: 405.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.5.1 CPython/3.8.18 Linux/6.11.0-1018-azure

File hashes

Hashes for letta_client-0.1.237-py3-none-any.whl
Algorithm Hash digest
SHA256 7d545269556ffbd34d864293839899de2c2070d2a30364201b292361380731af
MD5 2c778d13cdb579f858c6e3e0c42b7475
BLAKE2b-256 aba13faa0380d96377427f3eabdfeeb572e29e8cedf703ed9adb6d211e050be1

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page