Send LiteLLM events to Tinybird

LiteLLM is an LLM gateway that provides AI models access, fallbacks, and spend tracking across 100+ LLMs. It's a popular choice for many developers and organizations.

LiteLLM is open source and can be self-hosted.

To start sending LiteLLM events to Tinybird, first create a data source with this schema:

SCHEMA >
    `model` LowCardinality(String) `json:$.model` DEFAULT 'unknown',
    `messages` Array(Map(String, String)) `json:$.messages[:]` DEFAULT [],
    `user` String `json:$.user` DEFAULT 'unknown',
    `start_time` DateTime `json:$.start_time` DEFAULT now(),
    `end_time` DateTime `json:$.end_time` DEFAULT now(),
    `id` String `json:$.id` DEFAULT '',
    `stream` Boolean `json:$.stream` DEFAULT false,
    `call_type` LowCardinality(String) `json:$.call_type` DEFAULT 'unknown',
    `provider` LowCardinality(String) `json:$.provider` DEFAULT 'unknown',
    `api_key` String `json:$.api_key` DEFAULT '',
    `log_event_type` LowCardinality(String) `json:$.log_event_type` DEFAULT 'unknown',
    `llm_api_duration_ms` Float32 `json:$.llm_api_duration_ms` DEFAULT 0,
    `cache_hit` Boolean `json:$.cache_hit` DEFAULT false,
    `response_status` LowCardinality(String) `json:$.standard_logging_object_status` DEFAULT 'unknown',
    `response_time` Float32 `json:$.standard_logging_object_response_time` DEFAULT 0,
    `proxy_metadata` String `json:$.proxy_metadata` DEFAULT '',
    `organization` String `json:$.proxy_metadata.organization` DEFAULT '',
    `environment` String `json:$.proxy_metadata.environment` DEFAULT '',
    `project` String `json:$.proxy_metadata.project` DEFAULT '',
    `chat_id` String `json:$.proxy_metadata.chat_id` DEFAULT '',
    `response` String `json:$.response` DEFAULT '',
    `response_id` String `json:$.response.id`,
    `response_object` String `json:$.response.object` DEFAULT 'unknown',
    `response_choices` Array(String) `json:$.response.choices[:]` DEFAULT [],
    `completion_tokens` UInt16 `json:$.response.usage.completion_tokens` DEFAULT 0,
    `prompt_tokens` UInt16 `json:$.response.usage.prompt_tokens` DEFAULT 0,
    `total_tokens` UInt16 `json:$.response.usage.total_tokens` DEFAULT 0,
    `cost` Float32 `json:$.cost` DEFAULT 0,
    `exception` String `json:$.exception` DEFAULT '',
    `traceback` String `json:$.traceback` DEFAULT '',
    `duration` Float32 `json:$.duration` DEFAULT 0


ENGINE MergeTree
ENGINE_SORTING_KEY start_time, organization, project, model
ENGINE_PARTITION_KEY toYYYYMM(start_time)

Install the Tinybird AI Python SDK:

pip install tinybird-python-sdk[ai]

Finally, use the following handler in your app:

import litellm
from litellm import acompletion
from tb.litellm.handler import TinybirdLitellmAsyncHandler

customHandler = TinybirdLitellmAsyncHandler(
    api_url="https://api.us-east.aws.tinybird.co", 
    tinybird_token=os.getenv("TINYBIRD_TOKEN"), 
    datasource_name="litellm"
)

litellm.callbacks = [customHandler]

response = await acompletion(
    model="gpt-3.5-turbo", 
    messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
    stream=True
)

AI analytics template

Use the AI Analytics template to bootstrap a multi-tenant, user-facing AI analytics dashboard and LLM cost calculator for your AI models. You can fork it and make it your own.

See also