LLM_API

# Query the list of supported models

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio Access Token, [https://aistudio.baidu.com/account/accessToken](https://aistudio.baidu.com/account/accessToken),
    base_url="[https://aistudio.baidu.com/llm/lmapi/v3](https://aistudio.baidu.com/llm/lmapi/v3)",  # aistudio LLM api service domain
)

models = client.models.list()
for model in models.data:
    print(model.id)

# install from PyPI
pip install openai

import os
from openai import OpenAI

client = OpenAI(
     api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
     base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

chat_completion = client.chat.completions.create(
    messages=[
        {'role': 'system', 'content': 'You are a developer assistant for the AI Studio training platform. You are proficient in development-related knowledge and responsible for providing developers with search-related help and suggestions.'},
        {'role': 'user', 'content': 'Hello, please introduce AI Studio'}
    ],
    model="ernie-3.5-8k",
)

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

import os
from openai import OpenAI
import base64

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

# Generated image returned as a URL
images_url = client.images.generate(prompt="A white cat, red hat", model="Stable-Diffusion-XL", response_format="url")
print(images_url.data[0].url)

# Generated image returned as base64
images_base64 = client.images.generate(prompt="A black cat, blue hat", model="Stable-Diffusion-XL", response_format="b64_json")
# Save the generated images
for i, image in enumerate(images_base64.data):
    with open("image_{}.png".format(i), "wb") as f:
        f.write(base64.b64decode(image.b64_json))

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

embeddings = client.embeddings.create(
        model="embedding-v1",
        input=[
            "Recommend some food",
            "Tell me a story"
        ]
    )
print(embeddings)

import os
from openai import OpenAI

def get_response(messages):
    client = OpenAI(
        api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
        base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
    )
    completion = client.chat.completions.create(model="ernie-3.5-8k", messages=messages)
    return completion

messages = [
    {
        "role": "system",
        "content": "You are an AI Studio developer assistant. You are proficient in development-related knowledge and responsible for providing developers with search-related help and suggestions.",
    }
]

assistant_output = "Hello, I am the AI Studio developer assistant. How can I help you?"
print(f"""Input: "End" to end the conversation\n""")
print(f"Model output: {assistant_output}\n")
user_input = ""
while "End" not in user_input:
    user_input = input("Please enter: ")
    # Add user's question to the messages list
    messages.append({"role": "user", "content": user_input})
    assistant_output = get_response(messages).choices[0].message.content
    # Add the model's reply to the messages list
    messages.append({"role": "assistant", "content": assistant_output})
    print(f"Model output: {assistant_output}")
    print("\n")

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

completion = client.chat.completions.create(
    model="ernie-3.5-8k",
    messages=[
        {'role': 'system', 'content': 'You are a developer assistant for the AI Studio training platform. You are proficient in development-related knowledge and responsible for providing developers with search-related help and suggestions.'},
        {'role': 'user', 'content': 'Hello, please introduce AI Studio'}
    ],
    stream=True,
)

for chunk in completion:
    print(chunk.choices[0].delta.content or "", end="")

import os
from openai import AsyncOpenAI
import asyncio

client = AsyncOpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

async def main() -> None:
    chat_completion = await client.chat.completions.create(
        messages=[
            {'role': 'system', 'content': 'You are a developer assistant for the AI Studio training platform. You are proficient in development-related knowledge and responsible for providing developers with search-related help and suggestions.'},
            {'role': 'user', 'content': 'Hello, please introduce AI Studio'}
        ],
        model="ernie-3.5-8k",
    )
    print(chat_completion.choices[0].message.content)
    

asyncio.run(main())

{
    "web_search": {
        "enable": true,
        "enable_citation": true,
        "enable_trace": true,
        "enable_status": true,
        "search_num": 10,
        "reference_num": 5
    }
}

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

completion = client.chat.completions.create(
        model="ernie-4.0-turbo-8k",
        messages=[
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "text",
                            "text": "Who is the men's singles table tennis champion of the 2024 Olympics"
                        }
                    ]
                }
            ],
            extra_body={
                "web_search": {
                    "enable": True,
                    "enable_trace": True
                }
            },
        stream=True,
    )

search_result = []
for chunk in completion:
    if (len(chunk.choices) > 0):
        if (hasattr(chunk, 'search_results')):
            search_result.extend(chunk.search_results)
        print(chunk.choices[0].delta.content, end="", flush=True)
    
unique_dict = {}
for item in search_result:
    unique_dict[item["index"]] = item
print("\nReferences:\n")
for result in list(unique_dict.values()):
    print(str(result["index"]) + ". " + result["title"] + ". " + result["url"] + "\n")

{
  "model": "ernie-3.5-8k",
  "messages": [
    {
      "role": "user",
      "content": "Shanghai weather today"
    }
  ],
  "response_format": {
    "type": "text" //Can be replaced with json_object, json_schema
  }
}

  Since weather information is updated in real-time, I cannot directly provide the precise weather conditions for Shanghai today.\n\nTo get the latest Shanghai weather information, I recommend you check a weather forecast application, visit the official website of the meteorological bureau, or use other reliable weather information sources. These platforms usually provide detailed real-time weather data such as temperature, humidity, wind speed, precipitation probability, etc., as well as weather forecasts for the next few days.\n\nHope these suggestions are helpful to you!

  "{\n    \"Shanghai today's weather\": \"Since I cannot obtain real-time weather information, I am unable to provide the exact weather conditions for Shanghai today.\"\n}\n\nTo get real-time weather for Shanghai today, I recommend you check the weather app on your phone, visit the official website of the meteorological bureau, or use other reliable weather information sources. These channels usually provide the latest weather conditions, temperature, humidity, wind speed, and other detailed information."

from openai import OpenAI

client = OpenAI(
     api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
     base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

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"],
      },
    }
  }
]
messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]
completion = client.chat.completions.create(
  model="deepseek-v3",
  messages=messages,
  tools=tools,
  tool_choice="auto"
)

print(completion)

import os
from openai import OpenAI

client = OpenAI(
     api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
     base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

chat_completion = client.chat.completions.create(
    messages=[
        {'role': 'system', 'content': 'You are a developer assistant for the AI Studio training platform. You are proficient in development-related knowledge and responsible for providing developers with search-related help and suggestions.'},
        {'role': 'user', 'content': 'Hello, please introduce AI Studio'}
    ],
    model="deepseek-r1",
)

print(chat_completion.choices[0].message.reasoning_content)
print(chat_completion.choices[0].message.content)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

completion = client.chat.completions.create(
    model="deepseek-r1",
    messages=[
        {'role': 'system', 'content': 'You are a developer assistant for the AI Studio training platform. You are proficient in development-related knowledge and responsible for providing developers with search-related help and suggestions.'},
        {'role': 'user', 'content': 'Hello, please introduce AI Studio'}
    ],
    stream=True,
)

for chunk in completion:
    if (len(chunk.choices) > 0):
        if hasattr(chunk.choices[0].delta, 'reasoning_content') and chunk.choices[0].delta.reasoning_content:
            print(chunk.choices[0].delta.reasoning_content, end="", flush=True)
        else:
            print(chunk.choices[0].delta.content, end="", flush=True)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

completion = client.chat.completions.create(
        model="ernie-4.5-8k-preview",
        messages=[
            {
                'role': 'user', 'content': [
                    {
                        "type": "text",
                        "text": "Introduce a few famous attractions in Beijing"
                    }
                ]   
            }
        ]
    )

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

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

completion = client.chat.completions.create(
        model="ernie-4.5-8k-preview",
        messages=[
            {
                'role': 'user', 'content': [
                    {
                        "type": "text",
                        "text": "Introduce a few famous attractions in Beijing"
                    }
                ]   
            }
        ]
    )

for chunk in completion:
    if (len(chunk.choices) > 0):
        print(chunk.choices[0].delta.content, end="", flush=True)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

completion = client.chat.completions.create(
        model="ernie-4.5-8k-preview",
        messages=[
            {
                'role': 'user', 'content': [
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": "https://bucket-demo-bj.bj.bcebos.com/pic/wuyuetian.png",
                        "detail": "high"
                        }
                    }
                ]   
            }
        ],
        stream=True,
    )

for chunk in completion:
    if (len(chunk.choices) > 0):
        print(chunk.choices[0].delta.content, end="", flush=True)

import os
from openai import OpenAI


def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")
        
# Path to your image
image_path = "/image_1.png"

# Getting the Base64 string
base64_image = encode_image(image_path)

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

completion = client.chat.completions.create(
        model="ernie-4.5-8k-preview",
        messages=[
            {
                'role': 'user', 'content': [
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/jpeg;base64,{base64_image}"
                        }
                    }
                ]   
            }
        ],
        stream=True,
    )

for chunk in completion:
    if (len(chunk.choices) > 0):
        print(chunk.choices[0].delta.content, end="", flush=True)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

completion = client.chat.completions.create(
        model="ernie-4.5-8k-preview",
        messages=[
            {
                "role": "user",
                "content": [
                    {
                    "type": "text",
                    "text": "Which band is in the picture"
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://bucket-demo-bj.bj.bcebos.com/pic/wuyuetian.png",
                        "detail": "high"
                    }
                }
                ]
            }
        ],
        stream=True,
    )

for chunk in completion:
    if (len(chunk.choices) > 0):
        print(chunk.choices[0].delta.content, end="", flush=True)

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("AI_STUDIO_API_KEY"),  # Environment variable containing AI Studio access token, https://aistudio.baidu.com/account/accessToken,
    base_url="https://aistudio.baidu.com/llm/lmapi/v3",  # aistudio LLM api service domain
)

completion = client.chat.completions.create(
    model="default",
    temperature=0.6,
    messages= [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Describe this video"
                },
                {
                    "type": "video_url",
                    "video_url": {
                        "url": "https://bucket-demo-01.gz.bcebos.com/video/sea.mov", 
                        "fps": 1 
                    }
                }
            ]
        }
    ],
    stream=True
)

for chunk in completion:
    if (len(chunk.choices) > 0):
        print(chunk.choices[0].delta.content, end="", flush=True)