diff --git a/docs/my-website/docs/proxy/cost_tracking.md b/docs/my-website/docs/proxy/cost_tracking.md index 7f0a13f763f..35db752cbb6 100644 --- a/docs/my-website/docs/proxy/cost_tracking.md +++ b/docs/my-website/docs/proxy/cost_tracking.md @@ -17,7 +17,6 @@ LiteLLM automatically tracks spend for all known models. See our [model cost map **Step2** Send `/chat/completions` request - ```python @@ -860,6 +859,303 @@ Log specific key,value pairs as part of the metadata for a spend log :::info -Logging specific key,value pairs in spend logs metadata is an enterprise feature. [See here](./enterprise.md#tracking-spend-with-custom-metadata) +Logging specific key,value pairs in spend logs metadata is an enterprise feature. ::: + +Requirements: + +- Virtual Keys & a database should be set up, see [virtual keys](https://docs.litellm.ai/docs/proxy/virtual_keys) + +#### Usage - /chat/completions requests with special spend logs metadata + + + + + +```bash +curl -L -X POST 'http://0.0.0.0:4000/key/generate' \ +-H 'Authorization: Bearer sk-1234' \ +-H 'Content-Type: application/json' \ +-d '{ + "metadata": { + "spend_logs_metadata": { + "hello": "world" + } + } +} + +' +``` + + + + +```bash +curl -L -X POST 'http://0.0.0.0:4000/team/new' \ +-H 'Authorization: Bearer sk-1234' \ +-H 'Content-Type: application/json' \ +-d '{ + "metadata": { + "spend_logs_metadata": { + "hello": "world" + } + } +} + +' +``` + + + + + +Set `extra_body={"metadata": { }}` to `metadata` you want to pass + +```python +import openai +client = openai.OpenAI( + api_key="anything", + base_url="http://0.0.0.0:4000" +) + +# request sent to model set on litellm proxy, `litellm --model` +response = client.chat.completions.create( + model="gpt-3.5-turbo", + messages = [ + { + "role": "user", + "content": "this is a test request, write a short poem" + } + ], + extra_body={ + "metadata": { + "spend_logs_metadata": { + "hello": "world" + } + } + } +) + +print(response) +``` + +**Using Headers:** + +```python +import openai +client = openai.OpenAI( + api_key="sk-1234", + base_url="http://0.0.0.0:4000" +) + +# Pass spend logs metadata via headers +response = client.chat.completions.create( + model="gpt-3.5-turbo", + messages = [ + { + "role": "user", + "content": "this is a test request, write a short poem" + } + ], + extra_headers={ + "x-litellm-spend-logs-metadata": '{"user_id": "12345", "project_id": "proj_abc", "request_type": "chat_completion"}' + } +) + +print(response) +``` + + + + + + +```js +const openai = require('openai'); + +async function runOpenAI() { + const client = new openai.OpenAI({ + apiKey: 'sk-1234', + baseURL: 'http://0.0.0.0:4000' + }); + + try { + const response = await client.chat.completions.create({ + model: 'gpt-3.5-turbo', + messages: [ + { + role: 'user', + content: "this is a test request, write a short poem" + }, + ], + metadata: { + spend_logs_metadata: { // 👈 Key Change + hello: "world" + } + } + }); + console.log(response); + } catch (error) { + console.log("got this exception from server"); + console.error(error); + } +} + +// Call the asynchronous function +runOpenAI(); +``` + +**Using Headers:** + +```js +const openai = require('openai'); + +async function runOpenAI() { + const client = new openai.OpenAI({ + apiKey: 'sk-1234', + baseURL: 'http://0.0.0.0:4000' + }); + + try { + const response = await client.chat.completions.create({ + model: 'gpt-3.5-turbo', + messages: [ + { + role: 'user', + content: "this is a test request, write a short poem" + }, + ] + }, { + headers: { + 'x-litellm-spend-logs-metadata': '{"user_id": "12345", "project_id": "proj_abc", "request_type": "chat_completion"}' + } + }); + console.log(response); + } catch (error) { + console.log("got this exception from server"); + console.error(error); + } +} + +// Call the asynchronous function +runOpenAI(); +``` + + + + + +Pass `metadata` as part of the request body + +```shell +curl --location 'http://0.0.0.0:4000/chat/completions' \ + --header 'Content-Type: application/json' \ + --data '{ + "model": "gpt-3.5-turbo", + "messages": [ + { + "role": "user", + "content": "what llm are you" + } + ], + "metadata": { + "spend_logs_metadata": { + "hello": "world" + } + } +}' +``` + + + + + +Pass `x-litellm-spend-logs-metadata` as a request header with JSON string + +```shell +curl --location 'http://0.0.0.0:4000/chat/completions' \ + --header 'Content-Type: application/json' \ + --header 'Authorization: Bearer sk-1234' \ + --header 'x-litellm-spend-logs-metadata: {"user_id": "12345", "project_id": "proj_abc", "request_type": "chat_completion"}' \ + --data '{ + "model": "gpt-3.5-turbo", + "messages": [ + { + "role": "user", + "content": "what llm are you" + } + ] +}' +``` + + + + +```python +from langchain.chat_models import ChatOpenAI +from langchain.prompts.chat import ( + ChatPromptTemplate, + HumanMessagePromptTemplate, + SystemMessagePromptTemplate, +) +from langchain.schema import HumanMessage, SystemMessage + +chat = ChatOpenAI( + openai_api_base="http://0.0.0.0:4000", + model = "gpt-3.5-turbo", + temperature=0.1, + extra_body={ + "metadata": { + "spend_logs_metadata": { + "hello": "world" + } + } + } +) + +messages = [ + SystemMessage( + content="You are a helpful assistant that im using to make a test request to." + ), + HumanMessage( + content="test from litellm. tell me why it's amazing in 1 sentence" + ), +] +response = chat(messages) + +print(response) +``` + + + + + +#### Viewing Spend w/ custom metadata + +#### `/spend/logs` Request Format + +```bash +curl -X GET "http://0.0.0.0:4000/spend/logs?request_id=