LangChain API: 多模态输入

llm = CHatOllama() # ... just an example
message = {
    "role": "user",
    "content": [
        # ......
    ],
}

response = llm.invoke([message])
print(response.text())

"content": [
    {
        "type": "text",
        "text": "......", 
    }
]

{
    "type": "image",
    "source_type": "base64",
    "mime_type": "image/jpeg",  # or image/png, etc.
    "data": "<base64 data string>",
}

# OR...

{
    "type": "image",
    "source_type": "url",
    "url": "https://...",
}

{
    "type": "file",
    "source_type": "base64",
    "mime_type": "application/pdf",
    "data": "<base64 data string>",
}

{
    "type": "audio",
    "source_type": "base64",
    "mime_type": "audio/wav",  # or appropriate mime-type
    "data": "<base64 data string>",
}