Attaching files

You can attach files to an LLM call within a Deployment. This is useful when you want to extract data from a PDF or interact with its content.

The content of the files is incorporated into the initial system or user message. We recommend adjusting your prompt as you would when using variables in a prompt.

📘

Supported filetypes are pdf, txt, docx, csv, xls - 10MB max

🚧

Only the raw data is extracted, no images or objects. Also, encrypted files are not supported.

When to use Knowledge Base vs Attaching files

The need for full context understanding

Knowledge Bases and RAG (Retrieval Augmented Generation) retrieve relevant chunks, which works for focused queries but falls short for tasks like summarization that require full-document understanding.

Attaching files gives the LLM access to the entire document, ensuring it has the complete context.

For example, when summarizing reports, legal cases, or research papers, the LLM needs to process the full document to capture key details and connections that partial text retrieval can’t provide. Full context access leads to better comprehension and more accurate outputs, particularly for tasks requiring a holistic view, such as summarization and detailed analysis.

Dynamic document context

Unlike a static knowledge base, attached files can provide ad-hoc, context-specific documents for one-time or immediate use without the need for integration into a broader knowledge repository.

When a user is dealing with unique documents—such as one-off reports, meeting notes, or specific contracts—they can attach these files directly to a deployment. The LLM can instantly use these documents to provide answers or insights. This feature is especially useful for situations where time-sensitive or project-specific documents need to be used on the fly, giving flexibility to quickly incorporate new, temporary knowledge without modifying or updating the knowledge base.

Private or sensitive data

Due to privacy concerns, confidential or sensitive files (e.g., contracts and medical records) may not be suitable for a general knowledge base. Attaching files directly allows secure, temporary interaction with this data.

Attaching Files via the API

Upload a file

To attach files during generation, they need to be uploaded before the generation happens.

To upload a file use the following API call:

curl --location 'https://my.orq.ai/v2/files' \
--header 'Authorization: Bearer xxxxxx' \
--form 'purpose="retrieval"' \
--form 'file=@"/Users/cormick/Downloads/filename.pdf"'

Here is an example response, store the _id for future usage.

{
    "_id": "file_01JA5D27ZVW2N702Z0D3B1G8EK",
    "object_name": "files-api/workspaces/e747f6ac-19b0-47cd-8e79-0e1bf72b2a3e/retrieval/file_01JA5D27ZVW2N702Z0D3B1G8EK.vnd.openxmlformats-officedocument.spreadsheetml.sheet",
    "purpose": "retrieval",
    "file_name": "file_01JA5D27ZVW2N702Z0D3B1G8EK.vnd.openxmlformats-officedocument.spreadsheetml.sheet",
    "bytes": 5295,
    "created": "2024-10-14T11:36:54.189Z"
}

Attach a file during generation

When invoking a Deployment, attach your file id in the file_ids array as follow:

curl --location 'https://my.orq.ai/v2/deployments/invoke' \
--header 'Content-Type: application/json' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer xxxxx' \
--data '{
    "key": "deployment_key",
    "messages": [
        {
            "role": "user",
            "content": ""
        }
    ],
    "file_ids": [
        "file_01JA5D27ZVW2N702Z0D3B1G8EK"
    ]
}'