langcache

Developer-friendly & type-safe Python SDK specifically catered to leverage langcache API.

Summary

LangCache: API for managing a Redis LangCache service.

SDK Installation

The SDK can be installed with uv, pip, or poetry package managers.

uv

uv is a fast Python package installer and resolver, designed as a drop-in replacement for pip and pip-tools. It's recommended for its speed and modern Python tooling capabilities.

uv add langcache

PIP

PIP is the default package installer for Python, enabling easy installation and management of packages from PyPI via the command line.

pip install langcache

Poetry

Poetry is a modern tool that simplifies dependency management and package publishing by using a single pyproject.toml file to handle project metadata and dependencies.

poetry add langcache

Shell and script usage with uv

You can use this SDK in a Python shell with uv and the uvx command that comes with it like so:

uvx --from langcache python

It's also possible to write a standalone Python script without needing to set up a whole project like so:

#!/usr/bin/env -S uv run --script
# /// script
# requires-python = ">=3.10"
# dependencies = [
#     "langcache",
# ]
# ///

from langcache import LangCache

sdk = LangCache(
  # SDK arguments
)

# Rest of script here...

Once that is saved to a file, you can run it with uv run script.py where script.py can be replaced with the actual file name.

IDE Support

PyCharm

Generally, the SDK will work well with most IDEs out of the box. However, when using PyCharm, you can enjoy much better integration with Pydantic by installing an additional plugin.

• PyCharm Pydantic Plugin

SDK Example Usage

Save an entry

Save an entry to the cache

# Synchronous Example
from langcache import LangCache


with LangCache(
    "https://api.example.com",
    cache_id="<id>",
    api_key="<LANGCACHE_API_KEY>",
) as lang_cache:

    res = lang_cache.set(prompt="How does semantic caching work?", response="Semantic caching stores and retrieves data based on meaning, not exact matches.")

    # Handle response
    print(res)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from langcache import LangCache

async def main():

    async with LangCache(
        "https://api.example.com",
        cache_id="<id>",
        api_key="<LANGCACHE_API_KEY>",
    ) as lang_cache:

        res = await lang_cache.set_async(prompt="How does semantic caching work?", response="Semantic caching stores and retrieves data based on meaning, not exact matches.")

        # Handle response
        print(res)

asyncio.run(main())

Search for entries

Search for entries in the cache

# Synchronous Example
from langcache import LangCache


with LangCache(
    "https://api.example.com",
    cache_id="<id>",
    api_key="<LANGCACHE_API_KEY>",
) as lang_cache:

    res = lang_cache.search(prompt="How does semantic caching work?")

    # Handle response
    print(res)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from langcache import LangCache

async def main():

    async with LangCache(
        "https://api.example.com",
        cache_id="<id>",
        api_key="<LANGCACHE_API_KEY>",
    ) as lang_cache:

        res = await lang_cache.search_async(prompt="How does semantic caching work?")

        # Handle response
        print(res)

asyncio.run(main())

Delete an entry

Delete an entry from the cache by id

# Synchronous Example
from langcache import LangCache


with LangCache(
    "https://api.example.com",
    cache_id="<id>",
    api_key="<LANGCACHE_API_KEY>",
) as lang_cache:

    lang_cache.delete_by_id(entry_id="<id>")

    # Use the SDK ...

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from langcache import LangCache

async def main():

    async with LangCache(
        "https://api.example.com",
        cache_id="<id>",
        api_key="<LANGCACHE_API_KEY>",
    ) as lang_cache:

        await lang_cache.delete_by_id_async(entry_id="<id>")

        # Use the SDK ...

asyncio.run(main())

Delete entries

Delete entries based on attributes

# Synchronous Example
from langcache import LangCache


with LangCache(
    "https://api.example.com",
    cache_id="<id>",
    api_key="<LANGCACHE_API_KEY>",
) as lang_cache:

    res = lang_cache.delete_query(attributes={
        "language": "en",
        "topic": "ai",
    })

    # Handle response
    print(res)

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from langcache import LangCache

async def main():

    async with LangCache(
        "https://api.example.com",
        cache_id="<id>",
        api_key="<LANGCACHE_API_KEY>",
    ) as lang_cache:

        res = await lang_cache.delete_query_async(attributes={
            "language": "en",
            "topic": "ai",
        })

        # Handle response
        print(res)

asyncio.run(main())

Flush cache

Flush all entries from the cache

# Synchronous Example
from langcache import LangCache


with LangCache(
    "https://api.example.com",
    cache_id="<id>",
    api_key="<LANGCACHE_API_KEY>",
) as lang_cache:

    lang_cache.flush()

    # Use the SDK ...

The same SDK client can also be used to make asynchronous requests by importing asyncio.

# Asynchronous Example
import asyncio
from langcache import LangCache

async def main():

    async with LangCache(
        "https://api.example.com",
        cache_id="<id>",
        api_key="<LANGCACHE_API_KEY>",
    ) as lang_cache:

        await lang_cache.flush_async()

        # Use the SDK ...

asyncio.run(main())

Use exact search

Search for entries in the cache using both exact and semantic search

from langcache import LangCache
from langcache.models import SearchStrategy

with LangCache(
    server_url="https://api.example.com",
    cache_id="<id>",
    api_key="<LANGCACHE_API_KEY>",
) as lang_cache:

    res = lang_cache.search(prompt="How does semantic caching work?", search_strategies=[SearchStrategy.EXACT, SearchStrategy.SEMANTIC])

    # Handle response
    print(res)

Available Resources and Operations

Retries

Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.

To change the default retry strategy for a single API call, simply provide a RetryConfig object to the call:

from langcache import LangCache
from langcache.utils import BackoffStrategy, RetryConfig


with LangCache(
    "https://api.example.com",
    cache_id="<id>",
    api_key="<LANGCACHE_API_KEY>",
) as lang_cache:

    res = lang_cache.conversational_search(prompt="<value>",
        RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False))

    # Handle response
    print(res)

If you'd like to override the default retry strategy for all operations that support retries, you can use the retry_config optional parameter when initializing the SDK:

from langcache import LangCache
from langcache.utils import BackoffStrategy, RetryConfig


with LangCache(
    "https://api.example.com",
    retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
    cache_id="<id>",
    api_key="<LANGCACHE_API_KEY>",
) as lang_cache:

    res = lang_cache.conversational_search(prompt="<value>")

    # Handle response
    print(res)

Error Handling

LangCacheError is the base class for all HTTP error responses. It has the following properties:

Example

from langcache import LangCache, errors


with LangCache(
    "https://api.example.com",
    cache_id="<id>",
    api_key="<LANGCACHE_API_KEY>",
) as lang_cache:
    res = None
    try:

        res = lang_cache.conversational_search(prompt="<value>")

        # Handle response
        print(res)


    except errors.LangCacheError as e:
        # The base class for HTTP error responses
        print(e.message)
        print(e.status_code)
        print(e.body)
        print(e.headers)
        print(e.raw_response)

        # Depending on the method different errors may be thrown
        if isinstance(e, errors.BadRequestErrorResponseContent):
            print(e.data.title)  # str
            print(e.data.status)  # Optional[int]
            print(e.data.detail)  # Optional[str]
            print(e.data.instance)  # Optional[str]
            print(e.data.type)  # models.BadRequestErrorType

Error Classes

Primary errors:

• LangCacheError: The base class for HTTP error responses.
  • BadRequestErrorResponseContent: Request validation or input decoding failed. Status code 400.
  • AuthenticationErrorResponseContent: Authentication credentials are missing, malformed, or invalid. Status code 401.
  • ForbiddenErrorResponseContent: The caller is authenticated but not allowed to access the requested resource. Status code 403.
  • NotFoundErrorResponseContent: The requested resource does not exist. Status code 404.
  • PayloadTooLargeErrorResponseContent: The request payload exceeds the maximum supported size. Status code 413.
  • FailedDependencyErrorResponseContent: A dependent resource required to process the request is unavailable or unhealthy. Status code 424.
  • TooManyRequestsErrorResponseContent: The service rejected the request because rate limits were exceeded. Status code 429.
  • UnexpectedErrorResponseContent: The service failed with an unexpected internal error. Status code 500.

Custom HTTP Client

The Python SDK makes API calls using the httpx HTTP library. In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with your own HTTP client instance. Depending on whether you are using the sync or async version of the SDK, you can pass an instance of HttpClient or AsyncHttpClient respectively, which are Protocol's ensuring that the client has the necessary methods to make API calls. This allows you to wrap the client with your own custom logic, such as adding custom headers, logging, or error handling, or you can just pass an instance of httpx.Client or httpx.AsyncClient directly.

For example, you could specify a header for every request that this sdk makes as follows:

from langcache import LangCache
import httpx

http_client = httpx.Client(headers={"x-custom-header": "someValue"})
s = LangCache(client=http_client)

or you could wrap the client with your own custom logic:

from langcache import LangCache
from langcache.httpclient import AsyncHttpClient
import httpx

class CustomClient(AsyncHttpClient):
    client: AsyncHttpClient

    def __init__(self, client: AsyncHttpClient):
        self.client = client

    async def send(
        self,
        request: httpx.Request,
        *,
        stream: bool = False,
        auth: Union[
            httpx._types.AuthTypes, httpx._client.UseClientDefault, None
        ] = httpx.USE_CLIENT_DEFAULT,
        follow_redirects: Union[
            bool, httpx._client.UseClientDefault
        ] = httpx.USE_CLIENT_DEFAULT,
    ) -> httpx.Response:
        request.headers["Client-Level-Header"] = "added by client"

        return await self.client.send(
            request, stream=stream, auth=auth, follow_redirects=follow_redirects
        )

    def build_request(
        self,
        method: str,
        url: httpx._types.URLTypes,
        *,
        content: Optional[httpx._types.RequestContent] = None,
        data: Optional[httpx._types.RequestData] = None,
        files: Optional[httpx._types.RequestFiles] = None,
        json: Optional[Any] = None,
        params: Optional[httpx._types.QueryParamTypes] = None,
        headers: Optional[httpx._types.HeaderTypes] = None,
        cookies: Optional[httpx._types.CookieTypes] = None,
        timeout: Union[
            httpx._types.TimeoutTypes, httpx._client.UseClientDefault
        ] = httpx.USE_CLIENT_DEFAULT,
        extensions: Optional[httpx._types.RequestExtensions] = None,
    ) -> httpx.Request:
        return self.client.build_request(
            method,
            url,
            content=content,
            data=data,
            files=files,
            json=json,
            params=params,
            headers=headers,
            cookies=cookies,
            timeout=timeout,
            extensions=extensions,
        )

s = LangCache(async_client=CustomClient(httpx.AsyncClient()))

httpx2 (Pydantic's httpx fork)

httpx2 is Pydantic's maintained fork of httpx. To run this SDK on httpx2, call alias_httpx() at your program's entry point, before importing the SDK, so every import httpx — including the ones inside the SDK — resolves to httpx2:

import httpx2

httpx2.alias_httpx()

from langcache import LangCache

s = LangCache()

An SDK can also be generated against httpx2 directly, so it depends on the fork instead of httpx, by setting python.httpClientLibrary: httpx2 in gen.yaml.

Resource Management

The LangCache class implements the context manager protocol and registers a finalizer function to close the underlying sync and async HTTPX clients it uses under the hood. This will close HTTP connections, release memory and free up other resources held by the SDK. In short-lived Python programs and notebooks that make a few SDK method calls, resource management may not be a concern. However, in longer-lived programs, it is beneficial to create a single SDK instance via a context manager and reuse it across the application.

from langcache import LangCache
def main():

    with LangCache(
        "https://api.example.com",
        cache_id="<id>",
        api_key="<LANGCACHE_API_KEY>",
    ) as lang_cache:
        # Rest of application here...


# Or when using async:
async def amain():

    async with LangCache(
        "https://api.example.com",
        cache_id="<id>",
        api_key="<LANGCACHE_API_KEY>",
    ) as lang_cache:
        # Rest of application here...

Debugging

You can setup your SDK to emit debug logs for SDK requests and responses.

You can pass your own logger class directly into your SDK.

from langcache import LangCache
import logging

logging.basicConfig(level=logging.DEBUG)
s = LangCache(server_url="https://example.com", debug_logger=logging.getLogger("langcache"))

You can also enable a default debug logger by setting an environment variable LANGCACHE_DEBUG to true.

Development

Maturity

This SDK is in beta, and there may be breaking changes between versions without a major version update. Therefore, we recommend pinning usage to a specific package version. This way, you can install the same version each time without breaking changes unless you are intentionally looking for the latest version.