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 18:01:22 +00:00
parent 6f10ddb843
commit 64f9b1178e
No known key found for this signature in database
15 changed files with 55 additions and 55 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

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

@ -73,7 +73,7 @@ litellm.argilla_transformation_object = {
## LLM CALL ##
response = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello, how are you?"}],
)
```

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

@ -23,9 +23,9 @@ We will use the `--config` to set `litellm.callbacks = ["azure_sentinel"]` this
```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: ["azure_sentinel"] # logs llm success + failure logs to Azure Sentinel
```
@ -80,7 +80,7 @@ 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",

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

@ -59,5 +59,5 @@ os.environ["LANGFUSE_PUBLIC_KEY"] = ""
os.environ["LANGFUSE_SECRET_KEY"] = ""
os.environ["LANGFUSE_HOST"] = ""
response = completion(model="gpt-3.5-turbo", messages=messages)
response = completion(model="gpt-4o", messages=messages)
```

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

@ -6,9 +6,9 @@ Send LiteLLM logs to any HTTP endpoint.
```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:
@ -74,7 +74,7 @@ Logs are sent as `StandardLoggingPayload` [objects](https://docs.litellm.ai/docs
{
"id": "chatcmpl-123",
"call_type": "litellm.completion",
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [...],
"response": {...},
"usage": {...},

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

@ -42,7 +42,7 @@ litellm.success_callback = ["greenscale"]
#openai call
response = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}]
metadata={
"greenscale_project": "acme-project",
@ -58,7 +58,7 @@ You can send any additional information to Greenscale by using the `metadata` fi
```python
#openai call with additional metadata
response = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
],

20
docs/my-website/docs/observability/humanloop.md
View file

@ -26,7 +26,7 @@ os.environ["HUMANLOOP_API_KEY"] = "" # [OPTIONAL] set here or in `.completion`
litellm.set_verbose = True # see raw request to provider
resp = litellm.completion(
model="humanloop/gpt-3.5-turbo",
model="humanloop/gpt-4o",
prompt_id="test-chat-prompt",
prompt_variables={"user_message": "this is used"}, # [OPTIONAL]
messages=[{"role": "user", "content": "<IGNORED>"}],
@ -43,9 +43,9 @@ resp = litellm.completion(
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: humanloop/gpt-3.5-turbo
model: humanloop/gpt-4o
prompt_id: "<humanloop_prompt_id>"
api_key: os.environ/OPENAI_API_KEY
```
@ -66,7 +66,7 @@ curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -90,7 +90,7 @@ 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",
@ -120,7 +120,7 @@ print(response)
POST Request Sent from LiteLLM:
curl -X POST \
https://api.openai.com/v1/ \
-d '{'model': 'gpt-3.5-turbo', 'messages': <YOUR HUMANLOOP PROMPT TEMPLATE>}'
-d '{'model': 'gpt-4o', 'messages': <YOUR HUMANLOOP PROMPT TEMPLATE>}'
```
## How to set model
@ -137,7 +137,7 @@ You can do `humanloop/<litellm_model_name>`
```python
litellm.completion(
model="humanloop/gpt-3.5-turbo", # or `humanloop/anthropic/claude-3-5-sonnet`
model="humanloop/gpt-4o", # or `humanloop/anthropic/claude-3-5-sonnet`
...
)
```
@ -147,9 +147,9 @@ litellm.completion(
```yaml
model_list:
- model_name: gpt-3.5-turbo
- model_name: gpt-4o
litellm_params:
model: humanloop/gpt-3.5-turbo # OR humanloop/anthropic/claude-3-5-sonnet
model: humanloop/gpt-4o # OR humanloop/anthropic/claude-3-5-sonnet
prompt_id: <humanloop_prompt_id>
api_key: os.environ/OPENAI_API_KEY
```
@ -170,7 +170,7 @@ This also returns the template model set on Humanloop.
... # your prompt template
}
],
"model": "gpt-3.5-turbo" # your template model
"model": "gpt-4o" # your template model
}
```

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

@ -38,7 +38,7 @@ litellm.success_callback = ["lago"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
],
@ -99,7 +99,7 @@ client = openai.OpenAI(
)
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
response = client.chat.completions.create(model="gpt-4o", messages = [
{
"role": "user",
"content": "this is a test request, write a short poem"
@ -125,7 +125,7 @@ os.environ["OPENAI_API_KEY"] = "anything"
chat = ChatOpenAI(
openai_api_base="http://0.0.0.0:4000",
model = "gpt-3.5-turbo",
model = "gpt-4o",
temperature=0.1,
extra_body={
"user": "my_customer_id" # 👈 whatever your customer id is

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

@ -61,7 +61,7 @@ litellm.callbacks = ["langfuse_otel"]
# Make LLM requests as usual
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
```
@ -168,7 +168,7 @@ All metadata fields available in the vanilla Langfuse integration are now **full
```python
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}],
metadata={
"generation_name": "welcome-message",

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

@ -75,7 +75,7 @@ litellm --config config.yaml
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",

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

@ -29,7 +29,7 @@ litellm.failure_callback = ["literalai"] # Log Errors to LiteralAI
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi 👋 - i'm openai"}
]
@ -59,7 +59,7 @@ literalai_client = LiteralClient()
def my_agent(question: str):
# agent logic here
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": question}
],
@ -100,7 +100,7 @@ literalai_client = LiteralClient(api_key="")
literalai_client.instrument_openai()
settings = {
"model": "gpt-3.5-turbo", # model you want to send litellm proxy
"model": "gpt-4o", # model you want to send litellm proxy
"temperature": 0,
# ... more settings
}

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

@ -48,7 +48,7 @@ litellm.callbacks = ["opik"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Why is tracking and evaluation of LLMs important?"}
]
@ -70,7 +70,7 @@ litellm.callbacks = ["opik"]
def streaming_function(input):
messages = [{"role": "user", "content": input}]
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=messages,
metadata = {
"opik": {
@ -92,9 +92,9 @@ chunks = list(response)
```yaml
model_list:
- model_name: gpt-3.5-turbo-testing
- model_name: gpt-4o-testing
litellm_params:
model: gpt-3.5-turbo
model: gpt-4o
api_key: os.environ/OPENAI_API_KEY
litellm_settings:
@ -118,7 +118,7 @@ curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
"model": "gpt-3.5-turbo-testing",
"model": "gpt-4o-testing",
"messages": [
{
"role": "user",
@ -156,7 +156,7 @@ litellm.callbacks = ["opik"]
messages = [{"role": "user", "content": input}]
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=messages,
metadata = {
"opik": {
@ -177,7 +177,7 @@ curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -210,7 +210,7 @@ curl --location --request POST 'http://0.0.0.0:4000/chat/completions' \
--header 'opik_thread_id: your-thread-id' \
--header 'opik_tags: ["streaming-test"]' \
--data '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",
@ -244,7 +244,7 @@ curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-key-from-step-1' \
-d '{
"model": "gpt-3.5-turbo",
"model": "gpt-4o",
"messages": [
{
"role": "user",

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

@ -10,9 +10,9 @@ PostHog is an open-source product analytics platform that helps you track and an
```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: ["posthog"]
@ -41,7 +41,7 @@ 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",
@ -102,7 +102,7 @@ litellm.success_callback = ["posthog"]
# openai call
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hi - i'm openai"}
],
@ -126,7 +126,7 @@ import litellm
litellm.success_callback = ["posthog"]
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hello world"}
],
@ -148,7 +148,7 @@ client = openai.OpenAI(
)
response = client.chat.completions.create(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hello world"}
],
@ -173,7 +173,7 @@ litellm.success_callback = ["posthog"]
# Use custom PostHog credentials for this specific request
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "Hello world"}
],
@ -197,7 +197,7 @@ import litellm
litellm.success_callback = ["posthog"]
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[
{"role": "user", "content": "This won't be logged"}
],

10
docs/my-website/docs/observability/raw_request_response.md
View file

@ -33,7 +33,7 @@ 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"}
]
@ -78,7 +78,7 @@ litellm.return_response_headers = True
os.environ["OPENAI_API_KEY"] = "your-api-key"
response = litellm.completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{ "content": "Hello, how are you?","role": "user"}]
)
@ -92,9 +92,9 @@ print(response._hidden_params)
```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/GROQ_API_KEY
litellm_settings:
@ -108,7 +108,7 @@ curl -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": "system", "content": "Use your tools smartly"},
{ "role": "user", "content": "What time is it now? Use your tool"}

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

@ -79,7 +79,7 @@ litellm.success_callback = ["langfuse"]
## 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
@ -89,7 +89,7 @@ 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

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

@ -66,7 +66,7 @@ litellm.failure_callback=["supabase"]
# openai call
response = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
user="ishaan22" # identify users
)
@ -87,7 +87,7 @@ Pass `user` to `litellm.completion` to map your llm call to an end-user
```python
response = completion(
model="gpt-3.5-turbo",
model="gpt-4o",
messages=[{"role": "user", "content": "Hi 👋 - i'm openai"}],
user="ishaan22" # identify users
)