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

(fix) proxy + docs: use openai.chat.completions.create instead of openai.ChatCompletions

Browse source
This commit is contained in:
ishaan-jaff 2023-11-13 08:24:24 -08:00
parent 60770e1eec
commit cf0ab7155e
10 changed files with 20 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -113,7 +113,7 @@ import openai
openai.api_base = "http://0.0.0.0:8000" openai.api_base = "http://0.0.0.0:8000"
print(openai.ChatCompletion.create(model="test", messages=[{"role":"user", "content":"Hey!"}])) print(openai.chat.completions.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))
``` ```
## Supported Provider ([Docs](https://docs.litellm.ai/docs/providers)) ## Supported Provider ([Docs](https://docs.litellm.ai/docs/providers))

2
docs/my-website/docs/providers/azure.md
View file

@ -109,7 +109,7 @@ model_list = [{ # list of model deployments
router = Router(model_list=model_list) router = Router(model_list=model_list)
# openai.ChatCompletion.create replacement # openai.chat.completions.create replacement
response = router.completion(model="gpt-3.5-turbo", response = router.completion(model="gpt-3.5-turbo",
messages=[{"role": "user", "content": "Hey, how's it going?"}] messages=[{"role": "user", "content": "Hey, how's it going?"}]

2
docs/my-website/docs/providers/ollama.md
View file

@ -115,7 +115,7 @@ print(openai.api_base)
print(f'LiteLLM: response from proxy with streaming') print(f'LiteLLM: response from proxy with streaming')
response = openai.ChatCompletion.create( response = openai.chat.completions.create(
model="ollama/llama2", model="ollama/llama2",
messages = [ messages = [
{ {

6
docs/my-website/docs/simple_proxy.md
View file

@ -33,7 +33,7 @@ import openai
openai.api_base = "http://0.0.0.0:8000" openai.api_base = "http://0.0.0.0:8000"
print(openai.ChatCompletion.create(model="test", messages=[{"role":"user", "content":"Hey!"}])) print(openai.chat.completions.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))
``` ```
### Supported LLMs ### Supported LLMs
@ -541,7 +541,7 @@ If you're repo let's you set model name, you can call the specific model by just
import openai import openai
openai.api_base = "http://0.0.0.0:8000" openai.api_base = "http://0.0.0.0:8000"
completion = openai.ChatCompletion.create(model="zephyr-alpha", messages=[{"role": "user", "content": "Hello world"}]) completion = openai.chat.completions.create(model="zephyr-alpha", messages=[{"role": "user", "content": "Hello world"}])
print(completion.choices[0].message.content) print(completion.choices[0].message.content)
``` ```
@ -551,7 +551,7 @@ If you're repo only let's you specify api base, then you can add the model name
import openai import openai
openai.api_base = "http://0.0.0.0:8000/openai/deployments/zephyr-alpha/chat/completions" # zephyr-alpha will be used openai.api_base = "http://0.0.0.0:8000/openai/deployments/zephyr-alpha/chat/completions" # zephyr-alpha will be used
completion = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}]) completion = openai.chat.completions.create(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}])
print(completion.choices[0].message.content) print(completion.choices[0].message.content)
``` ```

2
litellm/proxy/README.md
View file

@ -19,7 +19,7 @@ import openai
openai.api_base = "http://0.0.0.0:8000" openai.api_base = "http://0.0.0.0:8000"
print(openai.ChatCompletion.create(model="test", messages=[{"role":"user", "content":"Hey!"}])) print(openai.chat.completions.create(model="test", messages=[{"role":"user", "content":"Hey!"}]))
``` ```
[**See how to call Huggingface,Bedrock,TogetherAI,Anthropic, etc.**](https://docs.litellm.ai/docs/simple_proxy) [**See how to call Huggingface,Bedrock,TogetherAI,Anthropic, etc.**](https://docs.litellm.ai/docs/simple_proxy)

7
litellm/proxy/proxy_cli.py
View file

@ -125,11 +125,10 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
openai.api_base = api_base openai.api_base = api_base
openai.api_key = "temp-key" openai.api_key = "temp-key"
print(openai.api_base) print(openai.api_base)
response = openai.completions.create(model="gpt-3.5-turbo", prompt='this is a test request, write a short poem')
response = openai.Completion.create(model="gpt-3.5-turbo", prompt='this is a test request, write a short poem')
print(response) print(response)
response = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages = [ response = openai.chat.completions.create(model="gpt-3.5-turbo", messages = [
{ {
"role": "user", "role": "user",
"content": "this is a test request, write a short poem" "content": "this is a test request, write a short poem"
@ -138,7 +137,7 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
click.echo(f'LiteLLM: response from proxy {response}') click.echo(f'LiteLLM: response from proxy {response}')
click.echo(f'LiteLLM: response from proxy with streaming {response}') click.echo(f'LiteLLM: response from proxy with streaming {response}')
response = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages = [ response = openai.chat.completions.create(model="gpt-3.5-turbo", messages = [
{ {
"role": "user", "role": "user",
"content": "this is a test request, write a short poem" "content": "this is a test request, write a short poem"

4
litellm_server/tests/test_bedrock.py
View file

@ -4,7 +4,7 @@ print("making request")
openai.api_key = "anything" # this gets passed as a header openai.api_key = "anything" # this gets passed as a header
response = openai.ChatCompletion.create( response = openai.chat.completions.create(
model = "bedrock/anthropic.claude-instant-v1", model = "bedrock/anthropic.claude-instant-v1",
messages = [ messages = [
{ {
@ -22,7 +22,7 @@ response = openai.ChatCompletion.create(
print(response) print(response)
# response = openai.ChatCompletion.create( # response = openai.chat.completions.create(
# model = "gpt-3.5-turbo", # model = "gpt-3.5-turbo",
# messages = [ # messages = [
# { # {

8
litellm_server/tests/test_caching.py
View file

@ -4,7 +4,7 @@ dotenv.load_dotenv()
openai.api_key = os.getenv("ANTHROPIC_API_KEY") # this gets passed as a header openai.api_key = os.getenv("ANTHROPIC_API_KEY") # this gets passed as a header
response1 = openai.ChatCompletion.create( response1 = openai.chat.completions.create(
model = "claude-instant-1", model = "claude-instant-1",
messages = [ messages = [
{ {
@ -21,7 +21,7 @@ except:
time.sleep(1) # allow time for request to be stored time.sleep(1) # allow time for request to be stored
response2 = openai.ChatCompletion.create( response2 = openai.chat.completions.create(
model = "claude-instant-1", model = "claude-instant-1",
messages = [ messages = [
{ {
@ -39,7 +39,7 @@ except:
openai.api_key = os.getenv("OPENAI_API_KEY") openai.api_key = os.getenv("OPENAI_API_KEY")
try: try:
response3 = openai.ChatCompletion.create( response3 = openai.chat.completions.create(
model = "gpt-3.5-turbo", model = "gpt-3.5-turbo",
messages = [ messages = [
{ {
@ -58,7 +58,7 @@ except:
openai.api_key = os.getenv("ANTHROPIC_API_KEY") # this gets passed as a header openai.api_key = os.getenv("ANTHROPIC_API_KEY") # this gets passed as a header
# switch caching off using cache flag # switch caching off using cache flag
response4 = openai.ChatCompletion.create( response4 = openai.chat.completions.create(
model = "claude-instant-1", model = "claude-instant-1",
messages = [ messages = [
{ {

4
litellm_server/tests/test_openai.py
View file

@ -5,7 +5,7 @@ openai.api_key = "this can be anything"
print("making request") print("making request")
api_key = "" api_key = ""
response = openai.ChatCompletion.create( response = openai.chat.completions.create(
model = "gpt-3.5-turbo", model = "gpt-3.5-turbo",
messages = [ messages = [
{ {
@ -21,7 +21,7 @@ response = openai.ChatCompletion.create(
print(response) print(response)
response = openai.ChatCompletion.create( response = openai.chat.completions.create(
model = "gpt-3.5-turbo", model = "gpt-3.5-turbo",
messages = [ messages = [
{ {

4
litellm_server/tests/test_openrouter.py
View file

@ -4,7 +4,7 @@ openai.api_key = "this can be anything"
print("making request") print("making request")
api_key = "" api_key = ""
response = openai.ChatCompletion.create( response = openai.chat.completions.create(
model = "openrouter/google/palm-2-chat-bison", model = "openrouter/google/palm-2-chat-bison",
messages = [ messages = [
{ {
@ -20,7 +20,7 @@ response = openai.ChatCompletion.create(
print(response) print(response)
response = openai.ChatCompletion.create( response = openai.chat.completions.create(
model = "openrouter/google/palm-2-chat-bison", model = "openrouter/google/palm-2-chat-bison",
messages = [ messages = [
{ {