Document Commands¶

./rag-cli documents list COLLECTION_ID [OPTIONS]

./rag-cli documents list col_123abc

./rag-cli documents list col_123abc --filter "pdf"

./rag-cli documents list col_123abc --include-stats --format json

./rag-cli documents list col_123abc --sort created_at --order desc

./rag-cli documents upload COLLECTION_ID FILE_PATH [FILE_PATH...] [OPTIONS]

./rag-cli documents upload col_123abc report.pdf

./rag-cli documents upload col_123abc report.pdf presentation.pptx \
  --tags "research,quarterly" \
  --metadata "department=engineering" \
  --metadata "quarter=Q1-2024"

./rag-cli documents upload col_123abc ./documents/ \
  --recursive \
  --pattern "*.pdf" \
  --auto-title \
  --wait

./rag-cli documents upload col_123abc manual.pdf \
  --title "User Manual v2.1" \
  --description "Updated user manual with new features" \
  --tags "manual,user-guide,v2.1" \
  --wait

./rag-cli documents get COLLECTION_ID DOCUMENT_ID [OPTIONS]

./rag-cli documents get col_123abc doc_abc123

./rag-cli documents get col_123abc doc_abc123 \
  --include-chunks \
  --include-metadata \
  --format json

./rag-cli documents get col_123abc doc_abc123 --include-content

./rag-cli documents download COLLECTION_ID DOCUMENT_ID [OPTIONS]

./rag-cli documents download col_123abc doc_abc123

./rag-cli documents download col_123abc doc_abc123 \
  --output ./downloads/research-paper.pdf

./rag-cli documents download col_123abc doc_abc123 \
  --format text \
  --output research-paper.txt

./rag-cli documents download col_123abc doc_abc123 \
  --format json \
  --include-metadata \
  --output document-export.json

./rag-cli documents delete COLLECTION_ID DOCUMENT_ID [OPTIONS]

./rag-cli documents delete col_123abc doc_abc123

./rag-cli documents delete col_123abc doc_abc123 --force

./rag-cli documents delete col_123abc doc_abc123 \
  --backup \
  --backup-path ./backups/

./rag-cli documents reprocess COLLECTION_ID DOCUMENT_ID [OPTIONS]

./rag-cli documents reprocess col_123abc doc_abc123

./rag-cli documents reprocess col_123abc doc_abc123 \
  --chunk-size 1024 \
  --chunk-overlap 100 \
  --wait

./rag-cli documents reprocess col_123abc doc_abc123 --force --wait

#!/bin/bash
find ./documents -type f \( -name "*.pdf" -o -name "*.docx" -o -name "*.txt" \) | \
while read file; do
    echo "Uploading: $file"
    ./rag-cli documents upload col_123abc "$file" \
      --auto-title \
      --tags "batch-upload,$(date +%Y-%m)" \
      --metadata "source=directory-import"
done

#!/bin/bash
# Reprocess all documents after collection settings change
./rag-cli documents list col_123abc --format json | \
jq -r '.documents[] | select(.status == "processed") | .id' | \
while read doc_id; do
    echo "Reprocessing: $doc_id"
    ./rag-cli documents reprocess col_123abc "$doc_id"
done

#!/bin/bash
echo "📊 Document Health Check"
echo "======================="

# Check for failed documents
failed=$(./rag-cli documents list col_123abc --format json | \
         jq '[.documents[] | select(.status == "failed")] | length')
echo "Failed documents: $failed"

# Check for stuck processing
processing=$(./rag-cli documents list col_123abc --format json | \
            jq '[.documents[] | select(.status == "processing")] | length')
echo "Processing documents: $processing"

# List documents needing attention
if [ "$failed" -gt 0 ] || [ "$processing" -gt 0 ]; then
    echo ""
    echo "Documents needing attention:"
    ./rag-cli documents list col_123abc --format json | \
    jq -r '.documents[] | select(.status == "failed" or .status == "processing") | [.id, .title, .status] | @tsv' | \
    while IFS=$'\t' read -r id title status; do
        echo "  - $title ($id): $status"
    done
fi

#!/bin/bash
# Add department metadata to all documents
./rag-cli documents list col_123abc --format json | \
jq -r '.documents[].id' | \
while read doc_id; do
    ./rag-cli documents update col_123abc "$doc_id" \
      --metadata "department=engineering" \
      --metadata "reviewed=2024-01"
done

#!/bin/bash
echo "Document Metadata Report"
echo "======================="

./rag-cli documents list col_123abc --format json --include-stats | \
jq -r '.documents[] | [.title, .file_type, .size_bytes, .chunk_count, .tags] | @csv' > document-report.csv

echo "Report exported to: document-report.csv"

#!/bin/bash
collection_id="col_123abc"

echo "📊 Document Statistics for Collection: $collection_id"
echo "=================================================="

# Get collection info
info=$(./rag-cli documents list "$collection_id" --format json --include-stats)

# Total documents
total=$(echo "$info" | jq '.total')
echo "Total Documents: $total"

# File type distribution
echo ""
echo "File Types:"
echo "$info" | jq -r '.documents | group_by(.file_type) | .[] | [.[0].file_type, length] | @tsv' | \
while IFS=$'\t' read -r type count; do
    echo "  - ${type^^}: $count documents"
done

# Size statistics
echo ""
echo "Size Statistics:"
total_size=$(echo "$info" | jq '[.documents[].size_bytes] | add')
avg_size=$(echo "$info" | jq '[.documents[].size_bytes] | add / length')
echo "  - Total: $(numfmt --to=iec $total_size)"
echo "  - Average: $(numfmt --to=iec ${avg_size%.*})"

# Processing status
echo ""
echo "Processing Status:"
echo "$info" | jq -r '.documents | group_by(.status) | .[] | [.[0].status, length] | @tsv' | \
while IFS=$'\t' read -r status count; do
    echo "  - ${status^}: $count documents"
done

$ ./rag-cli documents get col_123abc invalid-doc-id
❌ Document not found

Document 'invalid-doc-id' does not exist in collection 'col_123abc'.

List available documents:
./rag-cli documents list col_123abc

$ ./rag-cli documents upload col_123abc image.jpg
❌ Upload failed

File 'image.jpg' has unsupported format: JPEG
Supported formats: PDF, DOCX, DOC, TXT, MD, RTF, ODT

Convert to supported format or use text extraction tool first.

$ ./rag-cli documents get col_123abc doc_failed123
📄 Document Details

ID: doc_failed123
Status: ❌ Processing Failed
Error: Text extraction failed - corrupted PDF

Retry options:
1. Re-upload original file: ./rag-cli documents upload col_123abc original-file.pdf
2. Force reprocess: ./rag-cli documents reprocess col_123abc doc_failed123 --force
3. Delete and retry: ./rag-cli documents delete col_123abc doc_failed123

$ ./rag-cli documents upload col_123abc large-file.pdf
❌ Upload failed

Collection storage quota exceeded.
Current usage: 4.8 GB / 5.0 GB limit
File size: 245 MB

Options:
1. Delete unused documents to free space
2. Contact administrator to increase quota
3. Split large file into smaller documents

./rag-cli --debug documents upload col_123abc problem-file.pdf

./rag-cli documents get col_123abc doc_123 --include-logs

./rag-cli documents validate col_123abc doc_123 --check-chunks --check-embeddings

#!/bin/bash
# Automated documentation update script

collection_id="col_docs"
docs_dir="./updated-docs"

echo "🔄 Updating documentation collection..."

# Upload new/updated documents
for file in "$docs_dir"/*.md; do
    if [ -f "$file" ]; then
        title=$(basename "$file" .md)

        # Check if document already exists
        if ./rag-cli documents list "$collection_id" --filter "$title" --format json | jq -e '.documents | length > 0' > /dev/null; then
            echo "Updating existing document: $title"
            doc_id=$(./rag-cli documents list "$collection_id" --filter "$title" --format json | jq -r '.documents[0].id')
            ./rag-cli documents delete "$collection_id" "$doc_id" --force
        fi

        echo "Uploading: $title"
        ./rag-cli documents upload "$collection_id" "$file" \
          --title "$title" \
          --tags "documentation,auto-updated" \
          --metadata "version=$(git rev-parse --short HEAD)" \
          --metadata "updated=$(date -Iseconds)"
    fi
done

echo "✅ Documentation update completed"

#!/bin/bash
# Complete document backup script

collection_id="$1"
backup_dir="./backups/$(date +%Y%m%d_%H%M%S)"

echo "📦 Creating document backup for collection: $collection_id"

mkdir -p "$backup_dir"

# Export document metadata
./rag-cli documents list "$collection_id" --format json --include-stats > "$backup_dir/documents.json"

# Download all documents
./rag-cli documents list "$collection_id" --format json | \
jq -r '.documents[] | [.id, .title, .filename] | @tsv' | \
while IFS=$'\t' read -r doc_id title filename; do
    echo "Backing up: $title"
    ./rag-cli documents download "$collection_id" "$doc_id" \
      --output "$backup_dir/$filename"
done

echo "✅ Backup completed: $backup_dir"
tar -czf "$backup_dir.tar.gz" -C "$(dirname "$backup_dir")" "$(basename "$backup_dir")"
echo "📦 Archive created: $backup_dir.tar.gz"