Idea: allow user to upload pictures of documents (i.e. eviction notices) and use openai to parse them

[apkostka]

[KentShikama]

Yeah file upload is an easy extension I've been thinking of too.

A fun thought is to have the AI actually fill out the various forms that are required by the courts. We do it manually for RecordSponge at https://github.com/codeforpdx/recordexpungPDX/blob/master/src/backend/expungeservice/endpoints/pdf.py. I see no reason that an AI couldn't write/execute this PDF filling Python code. That said I do think that we should try to keep things as simple as possible for the initial rollout and I'm hoping that the users will tell us if this is needed. Just to be clear though, I do think that file upload is basic enough that it probably is within the MVP scope in terms of product complexity.

[KentShikama]

@claude Are you able to implement this and put up a PR?

[github-actions]

Claude encountered an error —— View job

---

I'll analyze this and get back to you.

[KentShikama]

@claude Try again

[claude]

Claude encountered an error —— View job

---

I'll analyze this and get back to you.

[KentShikama]

@claude Try again

[claude]

Claude finished @KentShikama's task —— View job • claude/issue-39-20250522_180558 • Create PR ➔

---

I've implemented the file upload feature to allow users to upload pictures of documents like eviction notices. Here's what I've done:

Implementation Details

• Added frontend file upload component in Chat.tsx
• Created backend upload.py module for handling file uploads
• Added route for file upload endpoint in app.py
• Added auto-creation of uploads directory in persistent storage
• Updated dependency requirements for image processing

Features

• Users can upload images (png, jpg, jpeg) or PDF documents
• OpenAI's Vision API analyzes the documents for eviction notice details
• Analysis focuses on identifying deficiencies and issues with notices
• Results are seamlessly integrated into the chat history
• Files are securely stored with unique IDs in the persistent storage

Technical Details

• Frontend: Added file input with upload and analyze buttons
• Backend: Created a new endpoint for processing uploaded files
• Storage: Files stored in DATA_DIR/uploads with UUID filenames
• Security: Implemented filename sanitization and file type validation
• OpenAI: Using Vision API to extract and analyze document content

[apkostka]

Bumping as I think this should be part of the v1 release, along with #163.