Q: intecept private url then upload it to the conversation (ex private confluence)

[rossm-mf]

I am trying to see how to intercept a private confluence url and upload the document into the conversation using the confluence API.

It feels like using filter pipeline would be the best approach but when I look at the inlet body there quite a lot of generated stuff for upload

The follwing example if for a public url but I imagine it would be the same result for private. Basically adding a new new messages under task_body?

{
    "model": "casperhansen/llama-3-70b-instruct-awq",
    "messages": [
        {
            "role": "user",
            "content": "..."
        }
    ],
    "stream": False,
    "metadata": {
        "task": "autocomplete_generation",
        "task_body": {
            "model": "casperhansen/llama-3-70b-instruct-awq",
            "prompt": "summmerize this",
            "messages": [
                {
                    "id": "5b4e4cc5-f666-4488-a572-44b69fbc9461",
                    "parentId": None,
                    "childrenIds": [
                        "d807994c-9fdf-47f2-8285-7f91552dc377"
                    ],
                    "role": "user",
                    "content": "summmerize this",
                    "files": [
                        {
                            "type": "doc",
                            "name": "https://docs.gitlab.com/ee/user/project/wiki/",
                            "collection_name": "1f822c5738db1d2fbb06b3294fc8d247f6fc0e11d65e23537b6332456a64ba5",
                            "status": "uploaded",
                            "url": "https://docs.gitlab.com/ee/user/project/wiki/",
                            "error": "",
                            "file": {
                                "data": {
                                    "content": "..."
                                },
                                "meta": {
                                    "name": "https://docs.gitlab.com/ee/user/project/wiki/"
                                }
                            }
                        }
                    ],
                    "timestamp": 1739497906,
                    "models": [
                        "casperhansen/llama-3-70b-instruct-awq"
                    ]
                },
                {
                    "parentId": "5b4e4cc5-f666-4488-a572-44b69fbc9461",
                    "id": "d807994c-9fdf-47f2-8285-7f91552dc377",
                    "childrenIds": [],
                    "role": "assistant",
                    "content": "",
                    "model": "casperhansen/llama-3-70b-instruct-awq",
                    "modelName": "casperhansen/llama-3-70b-instruct-awq",
                    "modelIdx": 0,
                    "userContext": None,
                    "timestamp": 1739497906
                }
            ],
            "type": "search query",
            "stream": False
        },
        "chat_id": None
    }
}

[quzhixue-Kimi]

hi there,

There is one feature that I would like to ask:

How could I upload a pdf/excel/word document via open-webui, and the file uploaded could be received and parsed in customized pipeline? Such after receiving the file, I would lie to use ollama embedding, docling or minerU framework to parse my file.

Currently, after uploading the file via open-webui, it seems that the file could not be processed.

Any feedback is appreciated.

BR
Kimi