scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 109

docs(observability): use gpt-4o instead of gpt-3.5-turbo in examples

Browse source 
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
This commit is contained in:
Cursor Agent 2026-03-21 18:00:58 +00:00
parent ecab4713db
commit 0cda3d4ff8
No known key found for this signature in database
17 changed files with 65 additions and 65 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/my-website/docs/observability/agentops_integration.md
View file

@ -25,7 +25,7 @@ litellm.success_callback = ["agentops"]
# Make your LLM calls as usual
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello, how are you?"}],
)
```

6
docs/my-website/docs/observability/arize_integration.md
View file

@ -39,7 +39,7 @@ litellm.callbacks = ["arize"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]
@ -108,7 +108,7 @@ litellm.callbacks = ["arize"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
],
@ -170,7 +170,7 @@ client = openai.OpenAI(
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(
model="gpt-3.5-turbo",
model="gpt-4o",
messages = [
{
"role": "user",

4
docs/my-website/docs/observability/athina_integration.md
View file

@ -45,7 +45,7 @@ litellm.success_callback = ["athina"]
#openai call
response = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}]
)
```
@ -56,7 +56,7 @@ You can send some additional information to Athina by using the `metadata` field
```python
#openai call with additional metadata
response = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
],

12
docs/my-website/docs/observability/braintrust.md
View file

@ -23,7 +23,7 @@ litellm.callbacks = ["braintrust"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]
@ -43,9 +43,9 @@ BRAINTRUST_API_BASE="https://api.braintrustdata.com/v1"
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: gpt-3.5-turbo
model: gpt-4o
api_key: os.environ/OPENAI_API_KEY
litellm_settings:
@ -86,7 +86,7 @@ You can customize the span id, root span name and span parents in Braintrust log
```python
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
],
@ -105,7 +105,7 @@ Note: Other `metadata` can be included here as well when using the SDK.
```python
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
],
@ -151,7 +151,7 @@ client = openai.OpenAI(
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(
model="gpt-3.5-turbo",
model="gpt-4o",
messages = [
{
"role": "user",

12
docs/my-website/docs/observability/custom_callback.md
View file

@ -39,7 +39,7 @@ customHandler = MyCustomHandler()
litellm.callbacks = [customHandler]
## sync
response = completion(model="gpt-3.5-turbo", messages=[{ "role": "user", "content": "Hi 👋 - i'm openai"}],
response = completion(model="gpt-4o", messages=[{ "role": "user", "content": "Hi 👋 - i'm openai"}],
stream=True)
for chunk in response:
continue
@ -49,7 +49,7 @@ for chunk in response:
import asyncio
def async completion():
response = await acompletion(model="gpt-3.5-turbo", messages=[{ "role": "user", "content": "Hi 👋 - i'm openai"}],
response = await acompletion(model="gpt-4o", messages=[{ "role": "user", "content": "Hi 👋 - i'm openai"}],
stream=True)
async for chunk in response:
continue
@ -125,7 +125,7 @@ from litellm import completion
litellm.success_callback = [custom_callback]
response = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{
"role": "user",
@ -163,7 +163,7 @@ customHandler = MyCustomHandler()
litellm.callbacks = [customHandler]
def async completion():
response = await acompletion(model="gpt-3.5-turbo", messages=[{ "role": "user", "content": "Hi 👋 - i'm openai"}],
response = await acompletion(model="gpt-4o", messages=[{ "role": "user", "content": "Hi 👋 - i'm openai"}],
stream=True)
async for chunk in response:
continue
@ -186,7 +186,7 @@ async def test_chat_openai():
try:
# litellm.set_verbose = True
litellm.success_callback = [async_test_logging_fn]
response = await litellm.acompletion(model="gpt-3.5-turbo",
response = await litellm.acompletion(model="gpt-4o",
messages=[{
"role": "user",
"content": "Hi 👋 - i'm openai"
@ -238,7 +238,7 @@ def track_cost_callback(kwargs, completion_response, start_time, end_time):
litellm.success_callback = [track_cost_callback]
response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello"}])
response = completion(model="gpt-4o", messages=[{"role": "user", "content": "Hello"}])
```
### Log Inputs to LLMs

26
docs/my-website/docs/observability/datadog.md
View file

@ -26,9 +26,9 @@ We will use the `--config` to set `litellm.callbacks = ["datadog"]` this will lo
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: gpt-3.5-turbo
model: gpt-4o
litellm_settings:
callbacks: ["datadog"] # logs llm success + failure logs on datadog
service_callback: ["datadog"] # logs redis, postgres failures on datadog
@ -47,9 +47,9 @@ litellm_settings:
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: gpt-3.5-turbo
model: gpt-4o
litellm_settings:
callbacks: ["datadog_llm_observability"] # logs llm success logs on datadog
```
@ -103,7 +103,7 @@ Test Request
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -131,9 +131,9 @@ When redaction is enabled, the actual message content and response text will be
```yaml showLineNumbers title="config.yaml"
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: gpt-3.5-turbo
model: gpt-4o
litellm_settings:
callbacks: ["datadog_llm_observability"] # logs llm success logs on datadog
@ -148,7 +148,7 @@ litellm_settings:
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -193,9 +193,9 @@ All metrics include the following tags: `env`, `service`, `version`, `HOSTNAME`,
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: gpt-3.5-turbo
model: gpt-4o
litellm_settings:
success_callback: ["datadog_metrics"]
failure_callback: ["datadog_metrics"]
@ -219,7 +219,7 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer sk-1234' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [{"role": "user", "content": "hello"}]
}'
```
@ -242,9 +242,9 @@ We will use the `--config` to set `litellm.callbacks = ["datadog_cost_management
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: gpt-3.5-turbo
model: gpt-4o
litellm_settings:
callbacks: ["datadog_cost_management"]
```

2
docs/my-website/docs/observability/deepeval_integration.md
View file

@ -33,7 +33,7 @@ litellm.failure_callback = ["deepeval"]
try:
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "What's the weather like in San Francisco?"}
],

4
docs/my-website/docs/observability/helicone_integration.md
View file

@ -127,7 +127,7 @@ Helicone's AI Gateway provides [advanced functionality](https://docs.helicone.ai
"Helicone-Retry-Enabled": "true", # Enable retry mechanism
"helicone-retry-num": "3", # Set number of retries
"helicone-retry-factor": "2", # Set exponential backoff factor
"Helicone-Model-Override": "gpt-3.5-turbo-0613", # Override the model used for cost calculation
"Helicone-Model-Override": "gpt-4o-0613", # Override the model used for cost calculation
"Helicone-Session-Id": "session-abc-123", # Set session ID for tracking
"Helicone-Session-Path": "parent-trace/child-trace", # Set session path for hierarchical tracking
"Helicone-Omit-Response": "false", # Include response in logging (default behavior)
@ -333,7 +333,7 @@ Track multi-step and agentic LLM interactions using session IDs and paths:
Helicone-Retry-Enabled: "true"
helicone-retry-num: "3"
helicone-retry-factor: "2"
Helicone-Fallbacks: '["gpt-3.5-turbo", "gpt-4"]'
Helicone-Fallbacks: '["gpt-4o", "gpt-4"]'
environment_variables:
HELICONE_API_KEY: "your-helicone-key"

16
docs/my-website/docs/observability/langfuse_integration.md
View file

@ -62,7 +62,7 @@ litellm.success_callback = ["langfuse"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]
@ -93,7 +93,7 @@ litellm.success_callback = ["langfuse"]
# openai call
response = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
],
@ -129,7 +129,7 @@ litellm.success_callback = ["langfuse"]
# set custom langfuse trace params and generation params
response = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
],
@ -170,7 +170,7 @@ curl --location --request POST 'http://0.0.0.0:4000/chat/completions' \
--header 'langfuse_trace_user_id: user-id2' \
--header 'langfuse_trace_metadata: {"key":"value"}' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -234,7 +234,7 @@ litellm.failure_callback = ["langfuse"]
# Request 1 → Langfuse Project A
response_a = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello from team A"}],
langfuse_public_key="pk-lf-project-a...",
langfuse_secret_key="sk-lf-project-a...",
@ -243,7 +243,7 @@ response_a = completion(
# Request 2 → Langfuse Project B (different project)
response_b = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello from team B"}],
langfuse_public_key="pk-lf-project-b...",
langfuse_secret_key="sk-lf-project-b...",
@ -261,7 +261,7 @@ litellm.success_callback = ["langfuse"]
litellm.failure_callback = ["langfuse"]
response = await acompletion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hi"}],
langfuse_public_key="pk-lf-...",
langfuse_secret_key="sk-lf-...",
@ -300,7 +300,7 @@ os.environ['OPENAI_API_KEY']="sk-..."
litellm.success_callback = ["langfuse"]
chat = ChatLiteLLM(
model="gpt-3.5-turbo"
model="gpt-4o"
model_kwargs={
"metadata": {
"trace_user_id": "user-id2", # set langfuse Trace User ID

18
docs/my-website/docs/observability/langsmith_integration.md
View file

@ -46,7 +46,7 @@ litellm.callbacks = ["langsmith"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]
@ -58,9 +58,9 @@ response = litellm.completion(
1. Setup config.yaml
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: openai/gpt-3.5-turbo
model: openai/gpt-4o
api_key: os.environ/OPENAI_API_KEY
litellm_settings:
@ -78,7 +78,7 @@ curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-eWkpOhYaHiuIZV-29JDeTQ' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -117,7 +117,7 @@ litellm.callbacks = ["langsmith"]
litellm.langsmith_batch_size = 1 # 👈 KEY CHANGE
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]
@ -130,9 +130,9 @@ print(response)
1. Setup config.yaml
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: openai/gpt-3.5-turbo
model: openai/gpt-4o
api_key: os.environ/OPENAI_API_KEY
litellm_settings:
@ -151,7 +151,7 @@ curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-eWkpOhYaHiuIZV-29JDeTQ' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -184,7 +184,7 @@ os.environ['OPENAI_API_KEY']=""
litellm.success_callback = ["langsmith"]
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
],

2
docs/my-website/docs/observability/logfire_integration.md
View file

@ -52,7 +52,7 @@ litellm.success_callback = ["logfire"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]

2
docs/my-website/docs/observability/openmeter.md
View file

@ -44,7 +44,7 @@ litellm.callbacks = ["openmeter"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]

2
docs/my-website/docs/observability/phoenix_integration.md
View file

@ -42,7 +42,7 @@ litellm.callbacks = ["arize_phoenix"]
# OpenAI call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]

4
docs/my-website/docs/observability/promptlayer_integration.md
View file

@ -44,7 +44,7 @@ os.environ["OPENAI_API_KEY"], os.environ["COHERE_API_KEY"] = "", ""
litellm.success_callback = ["promptlayer"]
#openai call
response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}])
response = completion(model="gpt-4o", messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}])
#cohere call
response = completion(model="command-nightly", messages=[{"role": "user", "content": "Hi 👋 - i'm cohere"}])
@ -72,7 +72,7 @@ os.environ["OPENAI_API_KEY"], os.environ["COHERE_API_KEY"] = "", ""
litellm.success_callback = ["promptlayer"]
#openai call - log llm provider is openai
response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}], metadata={"provider": "openai"})
response = completion(model="gpt-4o", messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}], metadata={"provider": "openai"})
#cohere call - log llm provider is cohere
response = completion(model="command-nightly", messages=[{"role": "user", "content": "Hi 👋 - i'm cohere"}], metadata={"provider": "cohere"})

2
docs/my-website/docs/observability/sentry.md
View file

@ -44,7 +44,7 @@ os.environ["OPENAI_API_KEY"] = "your-openai-key"
# set bad key to trigger error
api_key="bad-key"
response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hey!"}], stream=True, api_key=api_key)
response = completion(model="gpt-4o", messages=[{"role": "user", "content": "Hey!"}], stream=True, api_key=api_key)
print(response)
```

14
docs/my-website/docs/observability/sumologic_integration.md
View file

@ -56,7 +56,7 @@ litellm.callbacks = ["sumologic"]
# OpenAI call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - I'm testing Sumo Logic integration"}
]
@ -70,9 +70,9 @@ response = litellm.completion(
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: openai/gpt-3.5-turbo
model: openai/gpt-4o
api_key: os.environ/OPENAI_API_KEY
litellm_settings:
@ -95,7 +95,7 @@ curl -L -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -123,7 +123,7 @@ Example payload:
{
"id": "chatcmpl-123",
"call_type": "litellm.completion",
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{"role": "user", "content": "Hello"}
],
@ -156,9 +156,9 @@ The Sumo Logic integration uses **NDJSON (newline-delimited JSON)** format by de
Each log entry is sent as a separate line in the HTTP request:
```
{"id":"chatcmpl-1","model":"gpt-3.5-turbo","response_cost":0.0001,...}
{"id":"chatcmpl-1","model":"gpt-4o","response_cost":0.0001,...}
{"id":"chatcmpl-2","model":"gpt-4","response_cost":0.0003,...}
{"id":"chatcmpl-3","model":"gpt-3.5-turbo","response_cost":0.0001,...}
{"id":"chatcmpl-3","model":"gpt-4o","response_cost":0.0001,...}
```
#### Benefits for Field Extraction Rules (FERs)

2
docs/my-website/docs/observability/wandb_integration.md
View file

@ -46,7 +46,7 @@ litellm.success_callback = ["wandb"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]