Cannot use ollama/llama3.3

[yazeedalrubyli]

**Is your feature request related to a problem? **
I can use Ollama models up to llama3.2. What about the new ones?

Describe the solution you'd like
Addeingsupport of models llama3.3, phi4

[PeriniM]

Hey @yazeedalrubyli do you get some errors? Have you tried explicitily setting the model_tokens in the graph config?

[PeriniM]

This should work

graph_config = {
    "llm": {
        "model": "ollama/llama3.3",
        "temperature": 0,
        "model_tokens": 4096
    },
    "verbose": True,
    "headless": False
}

[AceCodePt]

+1

graph_config = {
    "llm": {
        "model": "ollama/llama3.2",
        "temperature": 0,
        "model_tokens":10000,
        "format": "json",  # Ollama needs the format to be specified explicitly
        # "base_url": "http://localhost:11434", # set ollama URL arbitrarily
    },
    "verbose": True,
    "headless": False
}

Result with:
Token indices sequence length is longer than the specified maximum sequence length for this model (1385 > 1024). Running this sequence through the model will result in indexing errors

smart_scraper_graph = SmartScraperGraph(
    prompt="List all links",
    source="https://www.google.com/search?q=why+it+doesn%27t+work",
    schema=Properties,
    config=graph_config
)