Upload Tests

mkdir -p docs_wte
unzip -o "orange.zip" -d docs_wte/
unzip -o "orange (1).zip" -d docs_wte/

Archive:  orange.zip
  inflating: docs_wte/contrats-next-obs_ds_4765.pdf  (11.8 MB)
  inflating: docs_wte/contrats-next-obs_ann_4762.pdf  (3.6 MB)
  inflating: docs_wte/WTE - Cisco IP Conference Phone 8832.pdf  
  inflating: docs_wte/WTE - Formation WTE Hub Utilisateur - Profil Admin (2024-10-14).pdf  
  [... 27 more files ...]
  
Archive:  orange (1).zip
  inflating: docs_wte/WTE - App Webex WTE  (2024 Mai).pdf  

Total files extracted: 31

#!/bin/bash

DOCS_DIR="docs_wte"
API_URL="http://localhost:8000"
COLLECTION_ID="wte_cisco"

for file in "$DOCS_DIR"/*.pdf; do
    filename=$(basename "$file")
    echo "Uploading: $filename"
    
    curl -s -X POST "$API_URL/documents/upload" \
        -F "file=@$file" \
        -F "collection_id=$COLLECTION_ID" \
        -F "metadata={\"source\":\"WTE Orange\",\"type\":\"documentation\"}"
    
    sleep 0.5
done

chmod +x upload_wte_docs.sh
./upload_wte_docs.sh

[1/31] Upload: Cisco IP DECT 6823.pdf
✅ Uploadé - ID: e583c0e4-99ee-4bd1-8eca-6864deb3b26e

[2/31] Upload: contrats-next-obs_ann_4762.pdf
✅ Uploadé - ID: 60f6d04e-a2b7-4593-995f-0bba1a911dd4

[3/31] Upload: contrats-next-obs_ds_4765.pdf
✅ Uploadé - ID: d1e4bfe6-304a-420b-97e3-5abc5ea243e1

[... 28 more ...]

[31/31] Upload: WTE - Tuto Mon parcours en vie de solution_Vdiff.pdf
✅ Uploadé - ID: 1a6ce324-49af-403b-b97e-56b76b086047

Résumé:
Total:   31 fichiers
Succès:  31 fichiers
Échecs:  0 fichiers

curl -s http://localhost:8000/documents | jq '[.documents[] | select(.filename | contains("WTE") or contains("Cisco"))] | {total: length, processed: [.[] | select(.status == "processed")] | length}'

{
  "total": 28,
  "processed": 27,
  "pending": 0,
  "processing": 0
}

curl -s http://localhost:8000/documents | jq '.documents[] | {filename, status, size}'

{
  "filename": "WTE - Cisco IP Conference Phone 8832.pdf",
  "status": "processed",
  "id": "9323e356-033f-4768-bfca-a06ade88bde9"
}
{
  "filename": "WTE - Formation WTE Hub Utilisateur - Profil Admin (2024-10-14).pdf",
  "status": "processed",
  "id": "3466dc3e-a8c9-4924-86a8-c3346b4b8093"
}

curl http://localhost:6333/collections/default | jq '{vectors_count: .result.points_count, status: .result.status}'

{
  "vectors_count": 4,
  "status": "green"
}

{
  "vectors_count": 928,
  "status": "green"
}

curl -X POST http://localhost:8000/documents/upload \
  -F "file=@guide_openrag.txt" \
  -F "collection_id=default"

{
  "document_id": "ec526a49-4f4f-4110-9043-8cc28d142634",
  "filename": "guide_openrag.txt",
  "status": "uploaded",
  "message": "Document uploaded successfully and queued for processing"
}

curl -X POST http://localhost:8000/documents/upload \
  -F "file=@document.pdf" \
  -F "collection_id=test" \
  -F "metadata={\"author\":\"John Doe\",\"category\":\"manual\"}"

curl -X POST http://localhost:8000/documents/upload \
  -F "file=@image.jpg" \
  -F "collection_id=default"

curl -X POST http://localhost:8000/documents/upload \
  -F "collection_id=default"

sudo docker exec openrag-postgres psql -U openrag -d openrag_db \
  -c "SELECT COUNT(*) FROM documents WHERE status='processed';"

  count
-------
    28
(1 row)

sudo docker exec openrag-postgres psql -U openrag -d openrag_db \
  -c "SELECT COUNT(*) FROM document_chunks;"

  count
-------
   928
(1 row)