跳至主要內容

/interactions

功能支援備註
記錄可跨所有整合運作
串流
負載平衡介於受支援的模型之間
支援的 LLM 提供者所有 LiteLLM 支援的 CHAT COMPLETION 提供者openai, anthropic, bedrock, vertex_ai, gemini, azure, azure_ai 等。

LiteLLM Python SDK 使用方式

快速開始

Create Interaction
from litellm import create_interaction
import os

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

response = create_interaction(
model="gemini/gemini-2.5-flash",
input="Tell me a short joke about programming."
)

print(response.outputs[-1].text)

非同步使用方式

Async Create Interaction
from litellm import acreate_interaction
import os
import asyncio

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

async def main():
response = await acreate_interaction(
model="gemini/gemini-2.5-flash",
input="Tell me a short joke about programming."
)
print(response.outputs[-1].text)

asyncio.run(main())

串流

Streaming Interaction
from litellm import create_interaction
import os

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

response = create_interaction(
model="gemini/gemini-2.5-flash",
input="Write a 3 paragraph story about a robot.",
stream=True
)

for chunk in response:
print(chunk)

LiteLLM AI Gateway(Proxy)使用方式

設定

將以下內容加入您的 litellm proxy config.yaml:

config.yaml
model_list:
- model_name: gemini-flash
litellm_params:
model: gemini/gemini-2.5-flash
api_key: os.environ/GEMINI_API_KEY

啟動 litellm:

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

# RUNNING on http://0.0.0.0:4000

測試請求

Create Interaction
curl -X POST "http://localhost:4000/v1beta/interactions" \
-H "Authorization: Bearer sk-1234" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini/gemini-2.5-flash",
"input": "Tell me a short joke about programming."
}'

串流:

Streaming Interaction
curl -N -X POST "http://localhost:4000/v1beta/interactions" \
-H "Authorization: Bearer sk-1234" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini/gemini-2.5-flash",
"input": "Write a 3 paragraph story about a robot.",
"stream": true
}'

取得互動:

Get Interaction by ID
curl "http://localhost:4000/v1beta/interactions/{interaction_id}" \
-H "Authorization: Bearer sk-1234"

請求/回應格式

請求參數

參數類型必填說明
modelstringYes要使用的模型(例如:gemini/gemini-2.5-flash
inputstringYes互動的輸入文字
streambooleanNo啟用串流回應
toolsarrayNo模型可用的工具
system_instructionstringNo模型的系統指示
generation_configobjectNo生成設定
previous_interaction_idstringNo前一個互動的 ID,用於內容脈絡

回應格式

{
"id": "interaction_abc123",
"object": "interaction",
"model": "gemini-2.5-flash",
"status": "completed",
"created": "2025-01-15T10:30:00Z",
"updated": "2025-01-15T10:30:05Z",
"role": "model",
"outputs": [
{
"type": "text",
"text": "Why do programmers prefer dark mode? Because light attracts bugs!"
}
],
"usage": {
"total_input_tokens": 10,
"total_output_tokens": 15,
"total_tokens": 25
}
}

呼叫非 Interactions API 端點(/interactions/responses 橋接)

LiteLLM 讓您可以透過連到 LiteLLM 的 /responses 端點的橋接,呼叫非 Interactions API 模型。這對於呼叫 OpenAI、Anthropic,以及其他原生不支援 Interactions API 的提供者很有用。

Python SDK 使用方式

SDK Usage
import litellm
import os

# Set API key
os.environ["OPENAI_API_KEY"] = "your-openai-api-key"

# Non-streaming interaction
response = litellm.interactions.create(
model="gpt-4o",
input="Tell me a short joke about programming."
)

print(response.outputs[-1].text)

LiteLLM Proxy 使用方式

設定組態:

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

啟動 Proxy:

Start LiteLLM Proxy
litellm --config /path/to/config.yaml

# RUNNING on http://0.0.0.0:4000

發送請求:

non-Interactions API Model Request
curl http://localhost:4000/v1beta/interactions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "openai-model",
"input": "Tell me a short joke about programming."
}'

支援的提供者

提供者使用方式連結
Google AI Studio使用方式
其他所有 LiteLLM 提供者橋接使用方式