[Feature Request]: Add Resume Parsing Integration to Email Generator — Upload PDF Resume to Personalize Cold Outreach

[divyanshim27]

Summary

The Arachnode roadmap lists resume parsing as a planned and partially built feature (resume_parser.py exists in email-generator-service/). However, the dashboard UI has no interface for uploading a resume, and the gateway's /api/generate endpoint does not appear to expose resume context as a first-class parameter for email personalization. The infrastructure exists — it just needs to be wired up end-to-end.

Problem

• email-generator-service/resume_parser.py and RESUME_PARSER_EXAMPLES.md confirm parsing logic exists, but there is no upload interface in dashboard.html.
• The /api/generate endpoint accepts candidate_skills, candidate_role, and candidate_experience as optional body parameters, but these must be typed manually — there is no mechanism to auto-populate them from a parsed resume.
• Cold emails generated without resume context are generic and less likely to receive responses — the core value proposition of the email generator is undermined.
• The roadmap explicitly calls this out: "Add resume parsing module adapting outbound email drafting according to distinct required keywords mapped off CV text profiles." — this is a maintainer-endorsed feature.

Impact

• Without resume integration, every generated email requires manual skill/experience input, which defeats the automation purpose.
• Outreach quality is directly proportional to how well the email reflects the candidate's actual background.
• The existing resume_parser.py code goes largely unused in the actual user flow.

Proposed Solution

1. Add resume upload form to dashboard.html:

<div id="resume-upload-panel" class="panel">
  <h3>Upload Resume</h3>
  <input type="file" id="resume-file" accept=".pdf,.txt" />
  <button id="parse-resume-btn">Parse & Save</button>
  <div id="parsed-resume-preview"></div>
</div>

2. Add /api/resume/parse endpoint in the gateway:

@app.post("/api/resume/parse")
async def parse_resume(file: UploadFile = File(...)):
    content = await file.read()
    parsed = resume_parser.parse(content, file.content_type)
    # Store parsed context in session or DB for use by /api/generate
    return {"skills": parsed.skills, "experience": parsed.experience, "role": parsed.target_role}

3. Auto-populate /api/generate from stored resume context:

// In dashboard.html JS
async function generateWithResume(jobId, contactId) {
  const resumeCtx = JSON.parse(sessionStorage.getItem('parsed_resume') || '{}');
  const response = await fetch('/api/generate', {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({
      job_id: jobId,
      contact_id: contactId,
      template: 'cold_outreach',
      candidate_skills: resumeCtx.skills,
      candidate_role: resumeCtx.role,
      candidate_experience: resumeCtx.experience
    })
  });
}

Additional Notes

• I will update the email-generator-service to accept resume context from the gateway rather than requiring it to be embedded in each request.
• The parsed resume will be stored in sessionStorage on the frontend for the current browser session.
• I will add a "Resume Loaded" indicator in the dashboard showing which resume is currently active.

I'd love to be assigned this issue and implement it completely.

Labels: enhancement, feature, roadmap, help wanted, GSSoC 2026

[divyanshim27]

Hey @sharmavaibhav31 ,
Please assign it to me under GSSoC 2026.
/assign /claim /claim-assignment