Merge branch 'BerriAI:main' into main

docs/my-website/docs/observability/lago.md

@@ -0,0 +1,173 @@
+import Image from '@theme/IdealImage';
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+# Lago - Usage Based Billing
+
+[Lago](https://www.getlago.com/) offers a self-hosted and cloud, metering and usage-based billing solution.
+
+<Image img={require('../../img/lago.jpeg')} />
+
+## Quick Start
+Use just 1 lines of code, to instantly log your responses **across all providers** with Lago
+
+Get your Lago [API Key](https://docs.getlago.com/guide/self-hosted/docker#find-your-api-key)
+
+```python
+litellm.callbacks = ["lago"] # logs cost + usage of successful calls to lago
+```
+
+
+<Tabs>
+<TabItem value="sdk" label="SDK">
+
+```python
+# pip install lago 
+import litellm
+import os
+
+os.environ["LAGO_API_BASE"] = "" # http://0.0.0.0:3000
+os.environ["LAGO_API_KEY"] = ""
+os.environ["LAGO_API_EVENT_CODE"] = "" # The billable metric's code - https://docs.getlago.com/guide/events/ingesting-usage#define-a-billable-metric
+
+# LLM API Keys
+os.environ['OPENAI_API_KEY']=""
+
+# set lago as a callback, litellm will send the data to lago
+litellm.success_callback = ["lago"] 
+ 
+# openai call
+response = litellm.completion(
+  model="gpt-3.5-turbo",
+  messages=[
+    {"role": "user", "content": "Hi 👋 - i'm openai"}
+  ],
+  user="your_customer_id" # 👈 SET YOUR CUSTOMER ID HERE
+)
+```
+
+</TabItem>
+<TabItem value="proxy" label="PROXY">
+
+1. Add to Config.yaml
+```yaml
+model_list:
+- litellm_params:
+    api_base: https://openai-function-calling-workers.tasslexyz.workers.dev/
+    api_key: my-fake-key
+    model: openai/my-fake-model
+  model_name: fake-openai-endpoint
+
+litellm_settings:
+  callbacks: ["lago"] # 👈 KEY CHANGE
+```
+
+2. Start Proxy
+
+```
+litellm --config /path/to/config.yaml
+```
+
+3. Test it! 
+
+<Tabs>
+<TabItem value="curl" label="Curl">
+
+```bash
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--data ' {
+      "model": "fake-openai-endpoint",
+      "messages": [
+        {
+          "role": "user",
+          "content": "what llm are you"
+        }
+      ],
+      "user": "your-customer-id" # 👈 SET YOUR CUSTOMER ID
+    }
+'
+```
+</TabItem>
+<TabItem value="openai_python" label="OpenAI Python SDK">
+
+```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"
+    }
+], user="my_customer_id") # 👈 whatever your customer id is
+
+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
+import os 
+
+os.environ["OPENAI_API_KEY"] = "anything"
+
+chat = ChatOpenAI(
+    openai_api_base="http://0.0.0.0:4000",
+    model = "gpt-3.5-turbo",
+    temperature=0.1,
+    extra_body={
+        "user": "my_customer_id"  # 👈 whatever your customer id is
+    }
+)
+
+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>
+</TabItem>
+</Tabs>
+
+
+<Image img={require('../../img/lago_2.png')} />
+
+## Advanced - Lagos Logging object 
+
+This is what LiteLLM will log to Lagos
+
+```
+{
+    "event": {
+      "transaction_id": "<generated_unique_id>",
+      "external_customer_id": <litellm_end_user_id>, # passed via `user` param in /chat/completion call - https://platform.openai.com/docs/api-reference/chat/create
+      "code": os.getenv("LAGO_API_EVENT_CODE"), 
+      "properties": {
+          "input_tokens": <number>,
+          "output_tokens": <number>,
+          "model": <string>,
+          "response_cost": <number>, # 👈 LITELLM CALCULATED RESPONSE COST - https://github.com/BerriAI/litellm/blob/d43f75150a65f91f60dc2c0c9462ce3ffc713c1f/litellm/utils.py#L1473
+      }
+    }
+}
+```

docs/my-website/docs/observability/langsmith_integration.md

@@ -71,6 +71,23 @@ response = litellm.completion(
 )
 print(response)
 ```
+
+### Make LiteLLM Proxy use Custom `LANGSMITH_BASE_URL`
+
+If you're using a custom LangSmith instance, you can set the
+`LANGSMITH_BASE_URL` environment variable to point to your instance.
+For example, you can make LiteLLM Proxy log to a local LangSmith instance with
+this config:
+
+```yaml
+litellm_settings:
+  success_callback: ["langsmith"]
+
+environment_variables:
+  LANGSMITH_BASE_URL: "http://localhost:1984"
+  LANGSMITH_PROJECT: "litellm-proxy"
+```
+
 ## Support & Talk to Founders
 
 - [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)

docs/my-website/docs/observability/openmeter.md

@@ -20,7 +20,7 @@ Use just 2 lines of code, to instantly log your responses **across all providers
 Get your OpenMeter API Key from https://openmeter.cloud/meters
 
 ```python
-litellm.success_callback = ["openmeter"] # logs cost + usage of successful calls to openmeter
+litellm.callbacks = ["openmeter"] # logs cost + usage of successful calls to openmeter
 ```
 
 
@@ -28,7 +28,7 @@ litellm.success_callback = ["openmeter"] # logs cost + usage of successful calls
 <TabItem value="sdk" label="SDK">
 
 ```python
-# pip install langfuse 
+# pip install openmeter 
 import litellm
 import os
 
@@ -39,8 +39,8 @@ os.environ["OPENMETER_API_KEY"] = ""
 # LLM API Keys
 os.environ['OPENAI_API_KEY']=""
 
-# set langfuse as a callback, litellm will send the data to langfuse
-litellm.success_callback = ["openmeter"] 
+# set openmeter as a callback, litellm will send the data to openmeter
+litellm.callbacks = ["openmeter"] 
  
 # openai call
 response = litellm.completion(
@@ -64,7 +64,7 @@ model_list:
   model_name: fake-openai-endpoint
 
 litellm_settings:
-  success_callback: ["openmeter"] # 👈 KEY CHANGE
+  callbacks: ["openmeter"] # 👈 KEY CHANGE
 ```
 
 2. Start Proxy