Websuche verwenden

Web-Suche mit LiteLLM verwenden

Feature	Details
Unterstützte Endpunkte	- /chat/completions - /responses
Unterstützte Anbieter	openai
LiteLLM Kostenverfolgung	✅ Unterstützt
LiteLLM Version	v1.63.15-nightly oder höher

/chat/completions (litellm.completion)

Schnellstart

SDK

from litellm import completion

response = completion(
    model="openai/gpt-4o-search-preview",
    messages=[
        {
            "role": "user",
            "content": "What was a positive news story from today?",
        }
    ],
)

PROXY

1. Konfigurieren Sie config.yaml

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

2. Starten Sie den Proxy

litellm --config /path/to/config.yaml

3. Testen Sie es!

from openai import OpenAI

# Point to your proxy server
client = OpenAI(
    api_key="sk-1234",
    base_url="http://0.0.0.0:4000"
)

response = client.chat.completions.create(
    model="gpt-4o-search-preview",
    messages=[
        {
            "role": "user",
            "content": "What was a positive news story from today?"
        }
    ]
)

Suchkontextgröße

SDK

from litellm import completion

# Customize search context size
response = completion(
    model="openai/gpt-4o-search-preview",
    messages=[
        {
            "role": "user",
            "content": "What was a positive news story from today?",
        }
    ],
    web_search_options={
        "search_context_size": "low"  # Options: "low", "medium" (default), "high"
    }
)

PROXY

from openai import OpenAI

# Point to your proxy server
client = OpenAI(
    api_key="sk-1234",
    base_url="http://0.0.0.0:4000"
)

# Customize search context size
response = client.chat.completions.create(
    model="gpt-4o-search-preview",
    messages=[
        {
            "role": "user",
            "content": "What was a positive news story from today?"
        }
    ],
    web_search_options={
        "search_context_size": "low"  # Options: "low", "medium" (default), "high"
    }
)

/responses (litellm.responses)

Schnellstart

SDK

from litellm import responses

response = responses(
    model="openai/gpt-4o",
    input=[
        {
            "role": "user",
            "content": "What was a positive news story from today?"
        }
    ],
    tools=[{
        "type": "web_search_preview"  # enables web search with default medium context size
    }]
)

PROXY

1. Konfigurieren Sie config.yaml

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

2. Starten Sie den Proxy

litellm --config /path/to/config.yaml

3. Testen Sie es!

from openai import OpenAI

# Point to your proxy server
client = OpenAI(
    api_key="sk-1234",
    base_url="http://0.0.0.0:4000"
)

response = client.responses.create(
    model="gpt-4o",
    tools=[{
        "type": "web_search_preview"
    }],
    input="What was a positive news story from today?",
)

print(response.output_text)

Suchkontextgröße

SDK

from litellm import responses

# Customize search context size
response = responses(
    model="openai/gpt-4o",
    input=[
        {
            "role": "user",
            "content": "What was a positive news story from today?"
        }
    ],
    tools=[{
        "type": "web_search_preview",
        "search_context_size": "low"  # Options: "low", "medium" (default), "high"
    }]
)

PROXY

from openai import OpenAI

# Point to your proxy server
client = OpenAI(
    api_key="sk-1234",
    base_url="http://0.0.0.0:4000"
)

# Customize search context size
response = client.responses.create(
    model="gpt-4o",
    tools=[{
        "type": "web_search_preview",
        "search_context_size": "low"  # Options: "low", "medium" (default), "high"
    }],
    input="What was a positive news story from today?",
)

print(response.output_text)

Prüfen, ob ein Modell Web-Suche unterstützt

SDK

Verwenden Sie litellm.supports_web_search(model="openai/gpt-4o-search-preview") -> gibt True zurück, wenn das Modell Websuchen durchführen kann

assert litellm.supports_web_search(model="openai/gpt-4o-search-preview") == True

PROXY

1. OpenAI-Modelle in config.yaml definieren

model_list:
  - model_name: gpt-4o-search-preview
    litellm_params:
      model: openai/gpt-4o-search-preview
      api_key: os.environ/OPENAI_API_KEY
    model_info:
      supports_web_search: True

2. Führen Sie den Proxy-Server aus

litellm --config config.yaml

3. Rufen Sie /model_group/info auf, um zu prüfen, ob ein Modell Web-Suche unterstützt

curl -X 'GET' \
  'https://:4000/model_group/info' \
  -H 'accept: application/json' \
  -H 'x-api-key: sk-1234'

Erwartete Antwort

{
  "data": [
    {
      "model_group": "gpt-4o-search-preview",
      "providers": ["openai"],
      "max_tokens": 128000,
      "supports_web_search": true, # 👈 supports_web_search is true
    }
  ]
}