OpenAI

LiteLLM unterstützt OpenAI Chat + Embedding-Aufrufe.

Erforderliche API-Schlüssel

import os 
os.environ["OPENAI_API_KEY"] = "your-api-key"

Verwendung

import os 
from litellm import completion

os.environ["OPENAI_API_KEY"] = "your-api-key"

# openai call
response = completion(
    model = "gpt-4o", 
    messages=[{ "content": "Hello, how are you?","role": "user"}]
)

Verwendung - LiteLLM Proxy-Server

So rufen Sie OpenAI-Modelle mit dem LiteLLM Proxy-Server auf

1. Speichern Sie den Schlüssel in Ihrer Umgebung

export OPENAI_API_KEY=""

2. Proxy starten

config.yaml
config.yaml - Proxy für alle OpenAI-Modelle
CLI

model_list:
  - model_name: gpt-3.5-turbo
    litellm_params:
      model: openai/gpt-3.5-turbo                          # The `openai/` prefix will call openai.chat.completions.create
      api_key: os.environ/OPENAI_API_KEY
  - model_name: gpt-3.5-turbo-instruct
    litellm_params:
      model: text-completion-openai/gpt-3.5-turbo-instruct # The `text-completion-openai/` prefix will call openai.completions.create
      api_key: os.environ/OPENAI_API_KEY

Verwenden Sie dies, um alle OpenAI-Modelle mit einem API-Schlüssel hinzuzufügen. WARNUNG: Dies führt keine Lastverteilung durch. Das bedeutet, dass Anfragen an gpt-4, gpt-3.5-turbo und gpt-4-turbo-preview alle über diese Route laufen werden.

model_list:
  - model_name: "*"             # all requests where model not in your config go to this deployment
    litellm_params:
      model: openai/*           # set `openai/` to use the openai route
      api_key: os.environ/OPENAI_API_KEY

$ litellm --model gpt-3.5-turbo

# Server running on http://0.0.0.0:4000

3. Testen

Curl-Anfrage
OpenAI v1.0.0+
Langchain

curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
      "model": "gpt-3.5-turbo",
      "messages": [
        {
          "role": "user",
          "content": "what llm are you"
        }
      ]
    }
'

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"
    }
])

print(response)

from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
    ChatPromptTemplate,
    HumanMessagePromptTemplate,
    SystemMessagePromptTemplate,
)
from langchain.schema import HumanMessage, SystemMessage

chat = ChatOpenAI(
    openai_api_base="http://0.0.0.0:4000", # set openai_api_base to the LiteLLM Proxy
    model = "gpt-3.5-turbo",
    temperature=0.1
)

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)

Optionale Schlüssel - OpenAI Organization, OpenAI API Base

import os 
os.environ["OPENAI_ORGANIZATION"] = "your-org-id"       # OPTIONAL
os.environ["OPENAI_BASE_URL"] = "https://your_host/v1"     # OPTIONAL

OpenAI Chat Completion Models

Modellname	Funktionsaufruf
gpt-4.1	`response = completion(model="gpt-4.1", messages=messages)`
gpt-4.1-mini	`response = completion(model="gpt-4.1-mini", messages=messages)`
gpt-4.1-nano	`response = completion(model="gpt-4.1-nano", messages=messages)`
o4-mini	`response = completion(model="o4-mini", messages=messages)`
o3-mini	`response = completion(model="o3-mini", messages=messages)`
o3	`response = completion(model="o3", messages=messages)`
o1-mini	`response = completion(model="o1-mini", messages=messages)`
o1-preview	`response = completion(model="o1-preview", messages=messages)`
gpt-4o-mini	`response = completion(model="gpt-4o-mini", messages=messages)`
gpt-4o-mini-2024-07-18	`response = completion(model="gpt-4o-mini-2024-07-18", messages=messages)`
gpt-4o	`response = completion(model="gpt-4o", messages=messages)`
gpt-4o-2024-08-06	`response = completion(model="gpt-4o-2024-08-06", messages=messages)`
gpt-4o-2024-05-13	`response = completion(model="gpt-4o-2024-05-13", messages=messages)`
gpt-4-turbo	`response = completion(model="gpt-4-turbo", messages=messages)`
gpt-4-turbo-preview	`response = completion(model="gpt-4-0125-preview", messages=messages)`
gpt-4-0125-preview	`response = completion(model="gpt-4-0125-preview", messages=messages)`
gpt-4-1106-preview	`response = completion(model="gpt-4-1106-preview", messages=messages)`
gpt-3.5-turbo-1106	`response = completion(model="gpt-3.5-turbo-1106", messages=messages)`
gpt-3.5-turbo	`response = completion(model="gpt-3.5-turbo", messages=messages)`
gpt-3.5-turbo-0301	`response = completion(model="gpt-3.5-turbo-0301", messages=messages)`
gpt-3.5-turbo-0613	`response = completion(model="gpt-3.5-turbo-0613", messages=messages)`
gpt-3.5-turbo-16k	`response = completion(model="gpt-3.5-turbo-16k", messages=messages)`
gpt-3.5-turbo-16k-0613	`response = completion(model="gpt-3.5-turbo-16k-0613", messages=messages)`
gpt-4	`response = completion(model="gpt-4", messages=messages)`
gpt-4-0314	`response = completion(model="gpt-4-0314", messages=messages)`
gpt-4-0613	`response = completion(model="gpt-4-0613", messages=messages)`
gpt-4-32k	`response = completion(model="gpt-4-32k", messages=messages)`
gpt-4-32k-0314	`response = completion(model="gpt-4-32k-0314", messages=messages)`
gpt-4-32k-0613	`response = completion(model="gpt-4-32k-0613", messages=messages)`

Diese unterstützen auch die Umgebungsvariable OPENAI_BASE_URL, die verwendet werden kann, um einen benutzerdefinierten API-Endpunkt anzugeben.

OpenAI Vision Models

Modellname	Funktionsaufruf
gpt-4o	`response = completion(model="gpt-4o", messages=messages)`
gpt-4-turbo	`response = completion(model="gpt-4-turbo", messages=messages)`
gpt-4-vision-preview	`response = completion(model="gpt-4-vision-preview", messages=messages)`

Verwendung

import os 
from litellm import completion

os.environ["OPENAI_API_KEY"] = "your-api-key"

# openai call
response = completion(
    model = "gpt-4-vision-preview", 
    messages=[
        {
            "role": "user",
            "content": [
                            {
                                "type": "text",
                                "text": "What’s in this image?"
                            },
                            {
                                "type": "image_url",
                                "image_url": {
                                "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
                                }
                            }
                        ]
        }
    ],
)

PDF-Dateianalyse

OpenAI hat einen neuen Nachrichtentyp file, mit dem Sie eine PDF-Datei übergeben und in eine strukturierte Ausgabe umwandeln lassen können. Mehr lesen

SDK
PROXY

import base64
from litellm import completion

with open("draconomicon.pdf", "rb") as f:
    data = f.read()

base64_string = base64.b64encode(data).decode("utf-8")

completion = completion(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "file",
                    "file": {
                        "filename": "draconomicon.pdf",
                        "file_data": f"data:application/pdf;base64,{base64_string}",
                    }
                },
                {
                    "type": "text",
                    "text": "What is the first dragon in the book?",
                }
            ],
        },
    ],
)

print(completion.choices[0].message.content)

Konfigurieren Sie config.yaml

model_list:
  - model_name: openai-model
    litellm_params:
      model: gpt-4o
      api_key: os.environ/OPENAI_API_KEY

Starten Sie den Proxy

litellm --config config.yaml

Testen Sie es!

curl -X POST 'http://0.0.0.0:4000/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{ 
    "model": "openai-model",
    "messages": [
        {"role": "user", "content": [
            {
                "type": "file",
                "file": {
                    "filename": "draconomicon.pdf",
                    "file_data": f"data:application/pdf;base64,{base64_string}",
                }
            }
        ]}
    ]
}'

OpenAI Fine Tuned Models

Modellname	Funktionsaufruf
fine-tuned `gpt-4-0613`	`response = completion(model="ft:gpt-4-0613", messages=messages)`
fine-tuned `gpt-4o-2024-05-13`	`response = completion(model="ft:gpt-4o-2024-05-13", messages=messages)`
fine-tuned `gpt-3.5-turbo-0125`	`response = completion(model="ft:gpt-3.5-turbo-0125", messages=messages)`
fine-tuned `gpt-3.5-turbo-1106`	`response = completion(model="ft:gpt-3.5-turbo-1106", messages=messages)`
fine-tuned `gpt-3.5-turbo-0613`	`response = completion(model="ft:gpt-3.5-turbo-0613", messages=messages)`

OpenAI Audio Transcription

LiteLLM unterstützt den OpenAI Audio Transcription-Endpunkt.

Unterstützte Modelle

Modellname	Funktionsaufruf
`whisper-1`	`response = completion(model="whisper-1", file=audio_file)`
`gpt-4o-transcribe`	`response = completion(model="gpt-4o-transcribe", file=audio_file)`
`gpt-4o-mini-transcribe`	`response = completion(model="gpt-4o-mini-transcribe", file=audio_file)`

SDK
PROXY

from litellm import transcription
import os 

# set api keys 
os.environ["OPENAI_API_KEY"] = ""
audio_file = open("/path/to/audio.mp3", "rb")

response = transcription(model="gpt-4o-transcribe", file=audio_file)

print(f"response: {response}")

Konfigurieren Sie config.yaml

model_list:
- model_name: gpt-4o-transcribe
  litellm_params:
    model: gpt-4o-transcribe
    api_key: os.environ/OPENAI_API_KEY
  model_info:
    mode: audio_transcription
    
general_settings:
  master_key: sk-1234

Starten Sie den Proxy

litellm --config config.yaml

Testen Sie es!

curl --location 'http://0.0.0.0:8000/v1/audio/transcriptions' \
--header 'Authorization: Bearer sk-1234' \
--form 'file=@"/Users/krrishdholakia/Downloads/gettysburg.wav"' \
--form 'model="gpt-4o-transcribe"'

Erweitert

Abrufen von OpenAI API-Antwortheadern

Stellen Sie litellm.return_response_headers = True ein, um rohe Antwortheader von OpenAI zu erhalten.

Sie können erwarten, dass Sie immer das Feld _response_headers von den Funktionen litellm.completion() und litellm.embedding() erhalten.

litellm.completion
litellm.completion + stream
litellm.embedding

litellm.return_response_headers = True

# /chat/completion
response = completion(
    model="gpt-4o-mini",
    messages=[
        {
            "role": "user",
            "content": "hi",
        }
    ],
)
print(f"response: {response}")
print("_response_headers=", response._response_headers)

litellm.return_response_headers = True

# /chat/completion
response = completion(
    model="gpt-4o-mini",
    stream=True,
    messages=[
        {
            "role": "user",
            "content": "hi",
        }
    ],
)
print(f"response: {response}")
print("response_headers=", response._response_headers)
for chunk in response:
    print(chunk)

litellm.return_response_headers = True

# embedding
embedding_response = litellm.embedding(
    model="text-embedding-ada-002",
    input="hello",
)

embedding_response_headers = embedding_response._response_headers
print("embedding_response_headers=", embedding_response_headers)

Erwartete Antwortheader von OpenAI

{
  "date": "Sat, 20 Jul 2024 22:05:23 GMT",
  "content-type": "application/json",
  "transfer-encoding": "chunked",
  "connection": "keep-alive",
  "access-control-allow-origin": "*",
  "openai-model": "text-embedding-ada-002",
  "openai-organization": "*****",
  "openai-processing-ms": "20",
  "openai-version": "2020-10-01",
  "strict-transport-security": "max-age=15552000; includeSubDomains; preload",
  "x-ratelimit-limit-requests": "5000",
  "x-ratelimit-limit-tokens": "5000000",
  "x-ratelimit-remaining-requests": "4999",
  "x-ratelimit-remaining-tokens": "4999999",
  "x-ratelimit-reset-requests": "12ms",
  "x-ratelimit-reset-tokens": "0s",
  "x-request-id": "req_cc37487bfd336358231a17034bcfb4d9",
  "cf-cache-status": "DYNAMIC",
  "set-cookie": "__cf_bm=E_FJY8fdAIMBzBE2RZI2.OkMIO3lf8Hz.ydBQJ9m3q8-1721513123-1.0.1.1-6OK0zXvtd5s9Jgqfz66cU9gzQYpcuh_RLaUZ9dOgxR9Qeq4oJlu.04C09hOTCFn7Hg.k.2tiKLOX24szUE2shw; path=/; expires=Sat, 20-Jul-24 22:35:23 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None, *cfuvid=SDndIImxiO3U0aBcVtoy1TBQqYeQtVDo1L6*Nlpp7EU-1721513123215-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None",
  "x-content-type-options": "nosniff",
  "server": "cloudflare",
  "cf-ray": "8a66409b4f8acee9-SJC",
  "content-encoding": "br",
  "alt-svc": "h3=\":443\"; ma=86400"
}

Paralleles Funktionsaufrufen

Eine detaillierte Anleitung zum parallelen Funktionsaufrufen mit litellm finden Sie hier.

import litellm
import json
# set openai api key
import os
os.environ['OPENAI_API_KEY'] = "" # litellm reads OPENAI_API_KEY from .env and sends the request
# Example dummy function hard coded to return the same weather
# In production, this could be your backend API or an external API
def get_current_weather(location, unit="fahrenheit"):
    """Get the current weather in a given location"""
    if "tokyo" in location.lower():
        return json.dumps({"location": "Tokyo", "temperature": "10", "unit": "celsius"})
    elif "san francisco" in location.lower():
        return json.dumps({"location": "San Francisco", "temperature": "72", "unit": "fahrenheit"})
    elif "paris" in location.lower():
        return json.dumps({"location": "Paris", "temperature": "22", "unit": "celsius"})
    else:
        return json.dumps({"location": location, "temperature": "unknown"})

messages = [{"role": "user", "content": "What's the weather like in San Francisco, Tokyo, and Paris?"}]
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_current_weather",
            "description": "Get the current weather in a given location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city and state, e.g. San Francisco, CA",
                    },
                    "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
                },
                "required": ["location"],
            },
        },
    }
]

response = litellm.completion(
    model="gpt-3.5-turbo-1106",
    messages=messages,
    tools=tools,
    tool_choice="auto",  # auto is default, but we'll be explicit
)
print("\nLLM Response1:\n", response)
response_message = response.choices[0].message
tool_calls = response.choices[0].message.tool_calls

Setzen von `extra_headers` für Completion-Aufrufe

import os 
from litellm import completion

os.environ["OPENAI_API_KEY"] = "your-api-key"

response = completion(
    model = "gpt-3.5-turbo", 
    messages=[{ "content": "Hello, how are you?","role": "user"}],
    extra_headers={"AI-Resource Group": "ishaan-resource"}
)

Setzen der Organization-ID für Completion-Aufrufe

Dies kann auf eine der folgenden Arten erfolgen:

Umgebungsvariable OPENAI_ORGANIZATION
Parameter an litellm.completion(model=model, organization="your-organization-id")
Einstellen als litellm.organization="your-organization-id"

import os 
from litellm import completion

os.environ["OPENAI_API_KEY"] = "your-api-key"
os.environ["OPENAI_ORGANIZATION"] = "your-org-id" # OPTIONAL

response = completion(
    model = "gpt-3.5-turbo", 
    messages=[{ "content": "Hello, how are you?","role": "user"}]
)

Setzen von `ssl_verify=False`

Dies geschieht durch die Einrichtung Ihres eigenen httpx.Client.

Für litellm.completion setzen Sie litellm.client_session=httpx.Client(verify=False).
Für litellm.acompletion setzen Sie litellm.aclient_session=AsyncClient.Client(verify=False).

import litellm, httpx

# for completion
litellm.client_session = httpx.Client(verify=False)
response = litellm.completion(
    model="gpt-3.5-turbo",
    messages=messages,
)

# for acompletion
litellm.aclient_session = httpx.AsyncClient(verify=False)
response = litellm.acompletion(
    model="gpt-3.5-turbo",
    messages=messages,
)

Verwendung von OpenAI Proxy mit LiteLLM

import os 
import litellm
from litellm import completion

os.environ["OPENAI_API_KEY"] = ""

# set custom api base to your proxy
# either set .env or litellm.api_base
# os.environ["OPENAI_BASE_URL"] = "https://your_host/v1"
litellm.api_base = "https://your_host/v1"


messages = [{ "content": "Hello, how are you?","role": "user"}]

# openai call
response = completion("openai/your-model-name", messages)

Wenn Sie die api_base dynamisch festlegen müssen, übergeben Sie sie einfach in den Completions - completions(...,api_base="your-proxy-api-base").

Weitere Informationen finden Sie unter Setzen von API-Base/Schlüsseln.

Weiterleiten der Org-ID für Proxy-Anfragen

Leiten Sie OpenAI Org-IDs vom Client mit dem Parameter forward_openai_org_id an OpenAI weiter.

Konfigurieren Sie config.yaml

model_list:
  - model_name: "gpt-3.5-turbo"
    litellm_params:
      model: gpt-3.5-turbo
      api_key: os.environ/OPENAI_API_KEY

general_settings:
    forward_openai_org_id: true # 👈 KEY CHANGE

Proxy starten

litellm --config config.yaml --detailed_debug

# RUNNING on http://0.0.0.0:4000

OpenAI-Aufruf tätigen

from openai import OpenAI
client = OpenAI(
    api_key="sk-1234",
    organization="my-special-org",
    base_url="http://0.0.0.0:4000"
)

client.chat.completions.create(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}])

In Ihren Logs sollten Sie die weitergeleitete Org-ID sehen.

LiteLLM:DEBUG: utils.py:255 - Request to litellm:
LiteLLM:DEBUG: utils.py:255 - litellm.acompletion(... organization='my-special-org',)

OpenAI

Erforderliche API-Schlüssel​

Verwendung​

Verwendung - LiteLLM Proxy-Server​

1. Speichern Sie den Schlüssel in Ihrer Umgebung​

2. Proxy starten​

3. Testen​

Optionale Schlüssel - OpenAI Organization, OpenAI API Base​

OpenAI Chat Completion Models​

OpenAI Vision Models​

Verwendung​

PDF-Dateianalyse​

OpenAI Fine Tuned Models​

OpenAI Audio Transcription​

Erweitert​

Abrufen von OpenAI API-Antwortheadern​

Paralleles Funktionsaufrufen​

Setzen von extra_headers für Completion-Aufrufe​

Setzen der Organization-ID für Completion-Aufrufe​

Setzen von ssl_verify=False​

Verwendung von OpenAI Proxy mit LiteLLM​

Weiterleiten der Org-ID für Proxy-Anfragen​

Erforderliche API-Schlüssel

Verwendung

Verwendung - LiteLLM Proxy-Server

1. Speichern Sie den Schlüssel in Ihrer Umgebung

2. Proxy starten

3. Testen

Optionale Schlüssel - OpenAI Organization, OpenAI API Base

OpenAI Chat Completion Models

OpenAI Vision Models

Verwendung

PDF-Dateianalyse

OpenAI Fine Tuned Models

OpenAI Audio Transcription

Erweitert

Abrufen von OpenAI API-Antwortheadern

Paralleles Funktionsaufrufen

Setzen von `extra_headers` für Completion-Aufrufe

Setzen der Organization-ID für Completion-Aufrufe

Setzen von `ssl_verify=False`

Verwendung von OpenAI Proxy mit LiteLLM

Weiterleiten der Org-ID für Proxy-Anfragen