Upd README configs

README.md

@@ -95,6 +95,40 @@ Open: `http://localhost:8000/static/`  •  Health: `GET /healthz`
 
 [Agent Assignment](https://huggingface.co/spaces/BinKhoaLe1812/EdSummariser/blob/main/AGENT_ASNM.md)
 
+### Manage ingestion_python as a git subtree (brief)
+
+Remotes (set once):
+
+```bash
+git remote add hfi1 https://huggingface.co/spaces/BinKhoaLe1812/StuddyBuddy_Ingestion1
+git remote add hfi2 https://huggingface.co/spaces/BinKhoaLe1812/StuddyBuddy_Ingestion2
+git remote add hfi3 https://huggingface.co/spaces/BinKhoaLe1812/StuddyBuddy_Ingestion3
+```
+
+Push ingestion_python to a Space:
+
+```bash
+# push current ingestion_python contents to hfi1 main
+git subtree push --prefix=ingestion_python hfi1 main
+
+# (alternatives)
+git subtree push --prefix=ingestion_python hfi2 main
+git subtree push --prefix=ingestion_python hfi3 main
+```
+
+Pull updates from a Space into the folder:
+
+```bash
+git fetch hfi1
+git subtree pull --prefix=ingestion_python hfi1 main --squash
+```
+
+Links:
+
+- [StuddyBuddy_Ingestion1](https://huggingface.co/spaces/BinKhoaLe1812/StuddyBuddy_Ingestion1)
+- [StuddyBuddy_Ingestion2](https://huggingface.co/spaces/BinKhoaLe1812/StuddyBuddy_Ingestion2)
+- [StuddyBuddy_Ingestion3](https://huggingface.co/spaces/BinKhoaLe1812/StuddyBuddy_Ingestion3)
+
 ### License
 
 Apache-2.0

ingestion_js/.gitignore

@@ -0,0 +1 @@
+.vercel

ingestion_js/README.md

@@ -24,6 +24,51 @@ Mirror of `ingestion_python` implemented as Next.js Route Handlers for Vercel.
 - `EMBED_BASE_URL`: remote embed service base, provides POST `/embed`
 - `NVIDIA_API`, or `NVIDIA_API_1..N`: caption API keys (optional)
 
+## Deploy to Vercel
+
+- Root directory: `ingestion_js`
+- Set Project Settings → Build Command: `next build`
+- Output: Next.js default
+- Environment Variables: set the vars above in Vercel
+
+## cURL Samples
+
+Replace `BASE` with your deployment URL.
+
+Health:
+
+```bash
+curl -X GET "$BASE/api/health" -H "Content-Type: application/json"
+```
+
+Upload:
+
+```bash
+curl -X POST "$BASE/api/upload" \
+  -F "user_id=YOUR_USER_ID" \
+  -F "project_id=YOUR_PROJECT_ID" \
+  -F "files=@../exefiles/Lecture5_ML.pdf" \
+  -F "files=@../exefiles/Lecture6_ANN_DL.pdf"
+```
+
+Status:
+
+```bash
+curl -X GET "$BASE/api/upload/status?job_id=YOUR_JOB_ID" -H "Content-Type: application/json"
+```
+
+List Files:
+
+```bash
+curl -X GET "$BASE/api/files?user_id=YOUR_USER_ID&project_id=YOUR_PROJECT_ID" -H "Content-Type: application/json"
+```
+
+Get Chunks:
+
+```bash
+curl -X GET "$BASE/api/files/chunks?user_id=YOUR_USER_ID&project_id=YOUR_PROJECT_ID&filename=Lecture5_ML.pdf&limit=5" -H "Content-Type: application/json"
+```
+
 ## Notes
 
 - Jobs are tracked in MongoDB collection `jobs` for serverless safety.

ingestion_js/app/api/health/route.ts

@@ -1,5 +1,5 @@
 import { NextResponse } from 'next/server'
-import { getMongo } from '@/lib/mongo'
+import { getMongo, ensureIndexes } from '@/lib/mongo'
 
 export const dynamic = 'force-dynamic'
 
@@ -8,6 +8,7 @@ export async function GET() {
   let mongodb_connected = false
   try {
     await mongo.db.command({ ping: 1 })
+    await ensureIndexes()
     mongodb_connected = true
   } catch {
     mongodb_connected = false

ingestion_js/app/api/upload/route.ts

@@ -6,21 +6,11 @@ import { buildCardsFromPages } from '@/lib/chunker'
 import { embedRemote } from '@/lib/embedder'
 import { deleteFileData, storeCards, upsertFileSummary } from '@/lib/mongo'
 import { cheapSummarize } from '@/lib/summarizer'
-import { createJob, getJob, updateJob } from '@/lib/jobs'
+import { createJob, updateJob } from '@/lib/jobs'
 
 export const dynamic = 'force-dynamic'
 export const runtime = 'nodejs'
 
-export async function GET(req: NextRequest) {
-  // Status endpoint: /api/upload?job_id=...
-  const { searchParams } = new URL(req.url)
-  const job_id = searchParams.get('job_id')
-  if (!job_id) return NextResponse.json({ error: 'job_id is required' }, { status: 400 })
-  const job = await getJob(job_id)
-  if (!job) return NextResponse.json({ error: 'job not found' }, { status: 404 })
-  return NextResponse.json({ job_id, status: job.status, total: job.total, completed: job.completed, last_error: job.last_error })
-}
-
 export async function POST(req: NextRequest) {
   const form = await req.formData()
   const user_id = String(form.get('user_id') || '')

ingestion_js/app/api/upload/status/route.ts

@@ -0,0 +1,14 @@
+import { NextRequest, NextResponse } from 'next/server'
+import { getJob } from '@/lib/jobs'
+
+export const dynamic = 'force-dynamic'
+export const runtime = 'nodejs'
+
+export async function GET(req: NextRequest) {
+  const { searchParams } = new URL(req.url)
+  const job_id = searchParams.get('job_id') || ''
+  if (!job_id) return NextResponse.json({ error: 'job_id is required' }, { status: 400 })
+  const job = await getJob(job_id)
+  if (!job) return NextResponse.json({ error: 'job not found' }, { status: 404 })
+  return NextResponse.json({ job_id, status: job.status, total: job.total, completed: job.completed, last_error: job.last_error })
+}