tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-05 20:23:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

(docs) langfuse logger

Browse Source
This commit is contained in:
ishaan-jaff
2023-10-17 12:05:30 -07:00
parent e4397e7e2a
commit 53e6ef62e7
1 changed files with 13 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/my-website/docs/observability/langfuse_integration.md
+13 -68
View File
@@ -7,9 +7,6 @@ Detailed production traces and a granular view on quality, cost and latency
<Image img={require('../../img/langfuse.png')} />
## Usage - log all LLM Providers (OpenAI, Azure, Anthropic, Cohere, Replicate, PaLM)
liteLLM provides `callbacks`, making it easy for you to log data depending on the status of your responses.
## Pre-Requisites
Ensure you have run `pip install langfuse` for this integration
```shell
@@ -17,6 +14,15 @@ pip install langfuse litellm
```
## Quick Start
Use just 2 lines of code, to instantly log your responses **across all providers** with Langfuse
<a target="_blank" href="https://colab.research.google.com/github/BerriAI/litellm/blob/main/cookbook/logging_observability/LiteLLM_Langfuse.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
Get your Langfuse API Keys from https://cloud.langfuse.com/
```python
litellm.success_callback = ["langfuse"]
```
```python
# pip install langfuse
import litellm
@@ -25,6 +31,10 @@ import os
# from https://cloud.langfuse.com/
os.environ["LANGFUSE_PUBLIC_KEY"] = ""
os.environ["LANGFUSE_SECRET_KEY"] = ""
# Optional, defaults to https://cloud.langfuse.com
os.environ["LANGFUSE_HOST"] # optional
# LLM API Keys
os.environ['OPENAI_API_KEY']=""
# set langfuse as a callback, litellm will send the data to langfuse
@@ -39,71 +49,6 @@ response = litellm.completion(
)
```
<a target="_blank" href="https://colab.research.google.com/github/BerriAI/litellm/blob/main/cookbook/logging_observability/LiteLLM_Langfuse.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
Get your Langfuse API Keys from https://cloud.langfuse.com/
Use just 2 lines of code, to instantly log your responses **across all providers** with langfuse:
```python
litellm.success_callback = ["langfuse"]
```
## API keys for Langfuse
Set the following variables in your .env
```python
# Required
os.environ["LANGFUSE_SECRET_KEY"]
os.environ["LANGFUSE_PUBLIC_KEY"]
# Optional, defaults to https://cloud.langfuse.com
os.environ["LANGFUSE_HOST"] # optional
```
## Complete code
```python
import litellm
from litellm import completion
import os
# from https://cloud.langfuse.com/
os.environ["LANGFUSE_PUBLIC_KEY"] = ""
os.environ["LANGFUSE_SECRET_KEY"] = ""
# OpenAI and Cohere keys
# You can use any of the litellm supported providers: https://docs.litellm.ai/docs/providers
os.environ['OPENAI_API_KEY']=""
os.environ['COHERE_API_KEY']=""
# set langfuse as a callback, litellm will send the data to langfuse
litellm.success_callback = ["langfuse"]
# openai call
response = completion(
model="gpt-3.5-turbo",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]
)
print(response)
# cohere call
response = completion(
model="command-nightly",
messages=[
{"role": "user", "content": "Hi 👋 - i'm cohere"}
]
)
print(response)
```
## Advanced
### Set Custom Generation names, pass metadata