phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

(docs) proxy

Browse source
This commit is contained in:
ishaan-jaff 2024-01-01 12:40:12 +05:30
parent a98d752f7b
commit 20236c1c69
4 changed files with 147 additions and 146 deletions
Download patch file Download diff file Expand all files Collapse all files

279
docs/my-website/docs/proxy/logging.md
View file

@ -3,7 +3,7 @@ import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem'; import TabItem from '@theme/TabItem';
# Logging - Custom Callbacks, OpenTelemetry, Langfuse, Sentry # Logging - Custom Callbacks, Langfuse, OpenTelemetry, Sentry
Log Proxy Input, Output, Exceptions using Custom Callbacks, Langfuse, OpenTelemetry, LangFuse, DynamoDB Log Proxy Input, Output, Exceptions using Custom Callbacks, Langfuse, OpenTelemetry, LangFuse, DynamoDB
@ -290,6 +290,145 @@ ModelResponse(
``` ```
## Logging Proxy Input/Output - Langfuse
We will use the `--config` to set `litellm.success_callback = ["langfuse"]` this will log all successfull LLM calls to langfuse
**Step 1** Install langfuse
```shell
pip install langfuse>=2.0.0
```
**Step 2**: Create a `config.yaml` file and set `litellm_settings`: `success_callback`
```yaml
model_list:
- model_name: gpt-3.5-turbo
litellm_params:
model: gpt-3.5-turbo
litellm_settings:
success_callback: ["langfuse"]
```
**Step 3**: Start the proxy, make a test request
Start proxy
```shell
litellm --config config.yaml --debug
```
Test Request
```
litellm --test
```
Expected output on Langfuse
<Image img={require('../../img/langfuse_small.png')} />
### Logging Metadata to Langfuse
<Tabs>
<TabItem value="Curl" label="Curl Request">
Pass `metadata` as part of the request body
```shell
curl --location 'http://0.0.0.0:8000/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-3.5-turbo",
"messages": [
{
"role": "user",
"content": "what llm are you"
}
],
"metadata": {
"generation_name": "ishaan-test-generation",
"generation_id": "gen-id22",
"trace_id": "trace-id22",
"trace_user_id": "user-id2"
}
}'
```
</TabItem>
<TabItem value="openai" label="OpenAI v1.0.0+">
Set `extra_body={"metadata": { }}` to `metadata` you want to pass
```python
import openai
client = openai.OpenAI(
api_key="anything",
base_url="http://0.0.0.0:8000"
)
# 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": {
"generation_name": "ishaan-generation-openai-client",
"generation_id": "openai-client-gen-id22",
"trace_id": "openai-client-trace-id22",
"trace_user_id": "openai-client-user-id2"
}
}
)
print(response)
```
</TabItem>
<TabItem value="langchain" label="Langchain">
```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://0.0.0.0:8000",
model = "gpt-3.5-turbo",
temperature=0.1,
extra_body={
"metadata": {
"generation_name": "ishaan-generation-langchain-client",
"generation_id": "langchain-client-gen-id22",
"trace_id": "langchain-client-trace-id22",
"trace_user_id": "langchain-client-user-id2"
}
}
)
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)
```
</TabItem>
</Tabs>
## OpenTelemetry - Traceloop ## OpenTelemetry - Traceloop
Traceloop allows you to log LLM Input/Output in the OpenTelemetry format Traceloop allows you to log LLM Input/Output in the OpenTelemetry format
@ -458,144 +597,6 @@ Here's the log view on Elastic Search. You can see the request `input`, `output`
<Image img={require('../../img/elastic_otel.png')} /> --> <Image img={require('../../img/elastic_otel.png')} /> -->
## Logging Proxy Input/Output - Langfuse
We will use the `--config` to set `litellm.success_callback = ["langfuse"]` this will log all successfull LLM calls to langfuse
**Step 1** Install langfuse
```shell
pip install langfuse>=2.0.0
```
**Step 2**: Create a `config.yaml` file and set `litellm_settings`: `success_callback`
```yaml
model_list:
- model_name: gpt-3.5-turbo
litellm_params:
model: gpt-3.5-turbo
litellm_settings:
success_callback: ["langfuse"]
```
**Step 3**: Start the proxy, make a test request
Start proxy
```shell
litellm --config config.yaml --debug
```
Test Request
```
litellm --test
```
Expected output on Langfuse
<Image img={require('../../img/langfuse_small.png')} />
### Logging Metadata to Langfuse
<Tabs>
<TabItem value="Curl" label="Curl Request">
Pass `metadata` as part of the request body
```shell
curl --location 'http://0.0.0.0:8000/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-3.5-turbo",
"messages": [
{
"role": "user",
"content": "what llm are you"
}
],
"metadata": {
"generation_name": "ishaan-test-generation",
"generation_id": "gen-id22",
"trace_id": "trace-id22",
"trace_user_id": "user-id2"
}
}'
```
</TabItem>
<TabItem value="openai" label="OpenAI v1.0.0+">
Set `extra_body={"metadata": { }}` to `metadata` you want to pass
```python
import openai
client = openai.OpenAI(
api_key="anything",
base_url="http://0.0.0.0:8000"
)
# 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": {
"generation_name": "ishaan-generation-openai-client",
"generation_id": "openai-client-gen-id22",
"trace_id": "openai-client-trace-id22",
"trace_user_id": "openai-client-user-id2"
}
}
)
print(response)
```
</TabItem>
<TabItem value="langchain" label="Langchain">
```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://0.0.0.0:8000",
model = "gpt-3.5-turbo",
temperature=0.1,
extra_body={
"metadata": {
"generation_name": "ishaan-generation-langchain-client",
"generation_id": "langchain-client-gen-id22",
"trace_id": "langchain-client-trace-id22",
"trace_user_id": "langchain-client-user-id2"
}
}
)
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)
```
</TabItem>
</Tabs>
## Logging Proxy Input/Output - DynamoDB ## Logging Proxy Input/Output - DynamoDB
We will use the `--config` to set We will use the `--config` to set

2
docs/my-website/docs/proxy/streaming_logging.md
View file

@ -1,4 +1,4 @@
# [Tutorial] Streaming token usage Logging # Track Token Usage (Streaming)
### Step 1 - Create your custom `litellm` callback class ### Step 1 - Create your custom `litellm` callback class
We use `litellm.integrations.custom_logger` for this, **more details about litellm custom callbacks [here](https://docs.litellm.ai/docs/observability/custom_callback)** We use `litellm.integrations.custom_logger` for this, **more details about litellm custom callbacks [here](https://docs.litellm.ai/docs/observability/custom_callback)**

8
docs/my-website/docs/proxy/users.md
View file

@ -1,4 +1,4 @@
# Set Budgets + Rate Limits per user # 💰 Budgets, Rate Limits per user
Requirements: Requirements:
@ -10,7 +10,7 @@ LiteLLM exposes a `/user/new` endpoint to create budgets for users, that persist
This is documented in the swagger (live on your server root endpoint - e.g. `http://0.0.0.0:8000/`). Here's an example request. This is documented in the swagger (live on your server root endpoint - e.g. `http://0.0.0.0:8000/`). Here's an example request.
```curl ```shell
curl --location 'http://localhost:8000/user/new' \ curl --location 'http://localhost:8000/user/new' \
--header 'Authorization: Bearer <your-master-key>' \ --header 'Authorization: Bearer <your-master-key>' \
--header 'Content-Type: application/json' \ --header 'Content-Type: application/json' \
@ -20,7 +20,7 @@ The request is a normal `/key/generate` request body + a `max_budget` field.
**Sample Response** **Sample Response**
```curl ```shell
{ {
"key": "sk-YF2OxDbrgd1y2KgwxmEA2w", "key": "sk-YF2OxDbrgd1y2KgwxmEA2w",
"expires": "2023-12-22T09:53:13.861000Z", "expires": "2023-12-22T09:53:13.861000Z",
@ -34,7 +34,7 @@ The request is a normal `/key/generate` request body + a `max_budget` field.
Set max parallel requests a user can make, when you create user keys - `/key/generate`. Set max parallel requests a user can make, when you create user keys - `/key/generate`.
```bash ```shell
curl --location 'http://0.0.0.0:8000/key/generate' \ curl --location 'http://0.0.0.0:8000/key/generate' \
--header 'Authorization: Bearer sk-1234' \ --header 'Authorization: Bearer sk-1234' \
--header 'Content-Type: application/json' \ --header 'Content-Type: application/json' \

4
docs/my-website/sidebars.js
View file

@ -111,10 +111,10 @@ const sidebars = {
"proxy/health", "proxy/health",
"proxy/call_hooks", "proxy/call_hooks",
"proxy/caching", "proxy/caching",
"proxy/streaming_logging",
"proxy/logging", "proxy/logging",
"proxy/cli", "proxy/streaming_logging",
"proxy/deploy", "proxy/deploy",
"proxy/cli",
] ]
}, },
"routing", "routing",