Tim Dolan

async def query_web_scraper(url: str) -> dict:
    scraper = WebScraper(headless=False)
    return await scraper.query_page_content(url)

# First API call: Send the query and function description to the model
response = ollama.chat(
    model=model,
    messages=messages,
    tools=[
        {
            'type': 'function',
            'function': {
                'name': 'query_web_scraper',
                'description': 'Scrapes the content of a web page and returns the structured JSON object with titles, articles, and associated links.',
                'parameters': {
                    'type': 'object',
                    'properties': {
                        'url': {
                            'type': 'string',
                            'description': 'The URL of the web page to scrape.',
                        },
                    },
                    'required': ['url'],
                },
            },
        },
    ]
)

docker pull apostacyh/vllm:lmcache-0.1.0

model=mistralai/Mistral-7B-Instruct-v0.2    # Replace with your model name
sudo docker run --runtime nvidia --gpus '"device=0"' \
    -v <Huggingface cache dir on your local machine>:/root/.cache/huggingface \
    -p 8000:8000 \
    --env "HF_TOKEN=<Your huggingface access token>" \
    --ipc=host \
    --network=host \
    apostacyh/vllm:lmcache-0.1.0 \
    --model $model --gpu-memory-utilization 0.6 --port 8000 \
    --lmcache-config-file /lmcache/LMCache/examples/example-local.yaml

# The second vLLM instance listens at port 8001
model=mistralai/Mistral-7B-Instruct-v0.2    # Replace with your model name
sudo docker run --runtime nvidia --gpus '"device=1"' \
    -v <Huggingface cache dir on your local machine>:/root/.cache/huggingface \
    -p 8001:8001 \
    --env "HF_TOKEN=<Your huggingface token>" \
    --ipc=host \
    --network=host \
    apostacyh/vllm:lmcache-0.1.0 \
    --model $model --gpu-memory-utilization 0.7 --port 8001 \
    --lmcache-config-file /lmcache/LMCache/examples/example.yaml