Spaces:
Running
Running
RidhiD. commited on
Commit Β·
1ebc860
1
Parent(s): c36e692
Ingestion script and test file
Browse files- .gitignore +1 -0
- .vscode/settings.json +59 -0
- cuad-demo-quadrant/CHUNKING_STRATEGY.md +224 -0
- cuad-demo-quadrant/upload_to_qdrant.py +350 -0
- tests/verify_collection.py +100 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
cuad-demo-quadrant/.env
|
.vscode/settings.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"python-envs.defaultEnvManager": "ms-python.python:venv",
|
| 3 |
+
|
| 4 |
+
// ββ File watcher exclusions (reduces inotify load & CPU usage) ββββββββββ
|
| 5 |
+
"files.watcherExclude": {
|
| 6 |
+
"**/.git/objects/**": true,
|
| 7 |
+
"**/.git/subtree-cache/**": true,
|
| 8 |
+
"**/__pycache__/**": true,
|
| 9 |
+
"**/*.pyc": true,
|
| 10 |
+
"**/*.pyo": true,
|
| 11 |
+
"**/.venv/**": true,
|
| 12 |
+
"**/venv/**": true,
|
| 13 |
+
"**/.tox/**": true,
|
| 14 |
+
"**/node_modules/**": true,
|
| 15 |
+
"**/dist/**": true,
|
| 16 |
+
"**/build/**": true,
|
| 17 |
+
"**/cuad_data/**": true,
|
| 18 |
+
"**/full_contract_pdf/**": true,
|
| 19 |
+
"**/*.pdf": true,
|
| 20 |
+
"**/*.PDF": true
|
| 21 |
+
},
|
| 22 |
+
|
| 23 |
+
// ββ Explorer exclusions (hides clutter from the sidebar) βββββββββββββββββ
|
| 24 |
+
"files.exclude": {
|
| 25 |
+
"**/__pycache__": true,
|
| 26 |
+
"**/*.pyc": true,
|
| 27 |
+
"**/*.pyo": true,
|
| 28 |
+
"**/.pytest_cache": true,
|
| 29 |
+
"**/*.egg-info": true
|
| 30 |
+
},
|
| 31 |
+
|
| 32 |
+
// ββ Search exclusions (speeds up Ctrl+Shift+F) βββββββββββββββββββββββββββ
|
| 33 |
+
"search.exclude": {
|
| 34 |
+
"**/__pycache__": true,
|
| 35 |
+
"**/.venv": true,
|
| 36 |
+
"**/venv": true,
|
| 37 |
+
"**/node_modules": true,
|
| 38 |
+
"**/dist": true,
|
| 39 |
+
"**/build": true,
|
| 40 |
+
"**/cuad_data": true,
|
| 41 |
+
"**/full_contract_pdf": true,
|
| 42 |
+
"**/*.pdf": true,
|
| 43 |
+
"**/*.PDF": true,
|
| 44 |
+
"**/*.json": false
|
| 45 |
+
},
|
| 46 |
+
|
| 47 |
+
// ββ Python analysis β limit what Pylance indexes βββββββββββββββββββββββββ
|
| 48 |
+
"python.analysis.exclude": [
|
| 49 |
+
"**/cuad_data/**",
|
| 50 |
+
"**/full_contract_pdf/**",
|
| 51 |
+
"**/__pycache__/**",
|
| 52 |
+
"**/.venv/**",
|
| 53 |
+
"**/venv/**"
|
| 54 |
+
],
|
| 55 |
+
"python.analysis.indexing": true,
|
| 56 |
+
"python.analysis.packageIndexDepths": [
|
| 57 |
+
{ "name": "", "depth": 2 }
|
| 58 |
+
]
|
| 59 |
+
}
|
cuad-demo-quadrant/CHUNKING_STRATEGY.md
ADDED
|
@@ -0,0 +1,224 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Text Chunking Strategy for CUAD Contract Embeddings
|
| 2 |
+
|
| 3 |
+
## Overview
|
| 4 |
+
|
| 5 |
+
The CUAD PDF ingestion pipeline uses a **smart hierarchical boundary-aware chunking strategy** to split contract text into semantically meaningful chunks before embedding and uploading to Qdrant vector database.
|
| 6 |
+
|
| 7 |
+
## Chunking Strategy
|
| 8 |
+
|
| 9 |
+
### Core Algorithm: `split_text_with_offsets()`
|
| 10 |
+
|
| 11 |
+
Located in `upload_to_qdrant.py`, the chunking function implements a **sliding window with intelligent boundary detection**:
|
| 12 |
+
|
| 13 |
+
```python
|
| 14 |
+
def split_text_with_offsets(text: str, chunk_size: int, chunk_overlap: int) -> list[dict]:
|
| 15 |
+
separators = ["\n\n", "\n", " ", ""]
|
| 16 |
+
# ... splits at best available boundary
|
| 17 |
+
```
|
| 18 |
+
|
| 19 |
+
### Strategy Details
|
| 20 |
+
|
| 21 |
+
#### 1. **Hierarchical Boundary Detection**
|
| 22 |
+
The algorithm attempts to break text at natural boundaries in this priority order:
|
| 23 |
+
- **Paragraph boundaries** (`"\n\n"`) β highest priority
|
| 24 |
+
- **Line boundaries** (`"\n"`)
|
| 25 |
+
- **Word boundaries** (` ` space)
|
| 26 |
+
- **Character boundaries** (`""`) β fallback only
|
| 27 |
+
|
| 28 |
+
This ensures chunks respect document structure and semantic coherence.
|
| 29 |
+
|
| 30 |
+
#### 2. **How It Works**
|
| 31 |
+
|
| 32 |
+
```
|
| 33 |
+
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 34 |
+
β Full Contract Text β
|
| 35 |
+
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 36 |
+
β
|
| 37 |
+
[Start at offset 0]
|
| 38 |
+
β
|
| 39 |
+
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 40 |
+
β Try to fit chunk_size (500 chars) of text β
|
| 41 |
+
β Then search backwards for nearest separator β
|
| 42 |
+
β [next_chunk_boundary] β found at \n\n β
|
| 43 |
+
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 44 |
+
β
|
| 45 |
+
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 46 |
+
β Yield Chunk 1: { text, char_start, char_end } β
|
| 47 |
+
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 48 |
+
β
|
| 49 |
+
[Advance by (end - overlap)]
|
| 50 |
+
[Move to next chunk with 50-char overlap]
|
| 51 |
+
β
|
| 52 |
+
[Repeat until text exhausted]
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
#### 3. **Overlap for Context Preservation**
|
| 56 |
+
|
| 57 |
+
- Default overlap: **50 characters**
|
| 58 |
+
- Ensures semantic continuity between chunks
|
| 59 |
+
- Important for vector search β similar content appears in adjacent chunks
|
| 60 |
+
- Example:
|
| 61 |
+
```
|
| 62 |
+
Chunk 1 ends: "...payment shall be made within 30 days."
|
| 63 |
+
Chunk 2 starts: "...within 30 days. Any late payment will incur..."
|
| 64 |
+
β overlapping context from Chunk 1
|
| 65 |
+
```
|
| 66 |
+
|
| 67 |
+
### Configuration Parameters
|
| 68 |
+
|
| 69 |
+
| Parameter | Default | Purpose |
|
| 70 |
+
|-----------|---------|---------|
|
| 71 |
+
| `CHUNK_SIZE` | 500 chars | Target size per chunk |
|
| 72 |
+
| `CHUNK_OVERLAP` | 50 chars | Context overlap between chunks |
|
| 73 |
+
| `MAX_DOCS` | 1000 chunks | Total chunks to upload |
|
| 74 |
+
| `ENCODE_BATCH_SIZE` | 32 | Chunks per embedding batch |
|
| 75 |
+
| `UPLOAD_BATCH_SIZE` | 100 | Chunks per Qdrant upsert |
|
| 76 |
+
|
| 77 |
+
## Rationale for This Strategy
|
| 78 |
+
|
| 79 |
+
### 1. **Semantic Preservation**
|
| 80 |
+
- Contracts are highly structured documents with clear logical boundaries (clauses, sections, subsections)
|
| 81 |
+
- Breaking at paragraph/line boundaries keeps related sentences together
|
| 82 |
+
- Avoids splitting mid-sentence or mid-clause, which would lose meaning
|
| 83 |
+
|
| 84 |
+
### 2. **RAG Optimization**
|
| 85 |
+
- For retrieval-augmented generation (RAG), chunks should be semantically cohesive
|
| 86 |
+
- When a chunk is retrieved as context, the model expects complete thoughts
|
| 87 |
+
- Boundary-aware chunking improves relevance of retrieved context
|
| 88 |
+
|
| 89 |
+
### 3. **Legal Document Specificity**
|
| 90 |
+
- Contract clauses often span multiple lines
|
| 91 |
+
- Paragraph breaks typically separate distinct legal obligations or definitions
|
| 92 |
+
- Natural language models (embedding models) perform better on semantically complete units
|
| 93 |
+
|
| 94 |
+
### 4. **Overlap for Robustness**
|
| 95 |
+
- Query might match content spanning two chunks
|
| 96 |
+
- Overlap ensures retrieval captures complete relevant context
|
| 97 |
+
- Trade-off: 50 chars is minimal overhead (10% of 500), benefits retrieval accuracy significantly
|
| 98 |
+
|
| 99 |
+
### 5. **Fallback Handling**
|
| 100 |
+
- If a 500-char window has no natural boundaries within the middle 50% (chunk_size // 2 = 250 chars), the algorithm falls back to character-level splitting
|
| 101 |
+
- This prevents infinite loops on text without natural boundaries (e.g., URLs, base64, code blocks)
|
| 102 |
+
- Rare in contract text but handles edge cases gracefully
|
| 103 |
+
|
| 104 |
+
## Implementation Flow
|
| 105 |
+
|
| 106 |
+
```
|
| 107 |
+
ββ Extract Text from PDF (all pages) ββββββββββββββββββ
|
| 108 |
+
β β
|
| 109 |
+
ββ Concatenate pages with \n\n separator β
|
| 110 |
+
β β
|
| 111 |
+
ββ Build page_map: map character offsets β page # β
|
| 112 |
+
β β
|
| 113 |
+
ββ For each PDF: β
|
| 114 |
+
β ββ Split full text into chunks using boundaries β
|
| 115 |
+
β β β
|
| 116 |
+
β ββ For each chunk: β
|
| 117 |
+
β ββ Calculate which pages it spans β
|
| 118 |
+
β ββ Store metadata: β
|
| 119 |
+
β β - doc_id, title, text β
|
| 120 |
+
β β - char_start/end (for PDF highlighting) β
|
| 121 |
+
β β - page_start/end (for citation) β
|
| 122 |
+
β β - pdf_path (for traceability) β
|
| 123 |
+
β β β
|
| 124 |
+
β ββ Yield for embedding β
|
| 125 |
+
β β
|
| 126 |
+
ββ Batch encode embeddings & upsert to Qdrant βββββββββ
|
| 127 |
+
```
|
| 128 |
+
|
| 129 |
+
## Metadata Attached to Each Chunk
|
| 130 |
+
|
| 131 |
+
```python
|
| 132 |
+
{
|
| 133 |
+
"doc_id": "contract-name-chunk-42", # Unique ID
|
| 134 |
+
"title": "contract-name", # PDF filename stem
|
| 135 |
+
"text": "...", # Actual text (500 chars)
|
| 136 |
+
"char_start": 1250, # Start offset in full text
|
| 137 |
+
"char_end": 1750, # End offset in full text
|
| 138 |
+
"page_start": 3, # Page(s) this chunk spans
|
| 139 |
+
"page_end": 4,
|
| 140 |
+
"pdf_path": "path/to/contract.pdf", # Relative path for retrieval
|
| 141 |
+
}
|
| 142 |
+
```
|
| 143 |
+
|
| 144 |
+
This metadata enables:
|
| 145 |
+
- **Exact citation**: Link search results directly to PDF pages
|
| 146 |
+
- **Traceability**: Know which contract and location each embedding came from
|
| 147 |
+
- **Transparency**: Show users the source text chunk alongside similarity scores
|
| 148 |
+
|
| 149 |
+
## Performance Characteristics
|
| 150 |
+
|
| 151 |
+
| Metric | Value | Notes |
|
| 152 |
+
|--------|-------|-------|
|
| 153 |
+
| Chunk size | ~500 chars | β 150β200 tokens for language models |
|
| 154 |
+
| Overlap | 50 chars | β 15β20 tokens |
|
| 155 |
+
| Effective unique content per chunk | ~450 chars | (500 - 50 overlap) |
|
| 156 |
+
| Max chunks per contract | Varies | Depends on contract length |
|
| 157 |
+
| Processing batches | 100-chunk upserts | Balances memory vs. network round-trips |
|
| 158 |
+
|
| 159 |
+
## Why NOT Other Strategies?
|
| 160 |
+
|
| 161 |
+
### β Fixed Character-only Splitting
|
| 162 |
+
- Would break contracts mid-clause
|
| 163 |
+
- "...party shall" | "...indemnify" (semantically broken)
|
| 164 |
+
- Poor retrieval quality
|
| 165 |
+
|
| 166 |
+
### β Sentence-based Splitting
|
| 167 |
+
- Contract "sentences" can be very long (100+ tokens)
|
| 168 |
+
- Would create inconsistent chunk sizes (too large for some)
|
| 169 |
+
- "Sentence" tokenization unreliable in legal text (e.g., "U.S." is not end of sentence)
|
| 170 |
+
|
| 171 |
+
### β No Overlap
|
| 172 |
+
- Query might start at the end of one chunk and continue into next
|
| 173 |
+
- Without overlap, key context would be missing from retrieved chunk
|
| 174 |
+
- Significantly degrades RAG quality
|
| 175 |
+
|
| 176 |
+
### β
This Strategy: Hierarchical Boundaries with Overlap
|
| 177 |
+
- Respects document structure (legal precision)
|
| 178 |
+
- Consistent encoding/retrieval (same chunk sizes across collection)
|
| 179 |
+
- Robust against edge cases (fallback to character level)
|
| 180 |
+
- Context-aware retrieval (overlap ensures complete thoughts)
|
| 181 |
+
|
| 182 |
+
## Usage Example
|
| 183 |
+
|
| 184 |
+
```bash
|
| 185 |
+
# Set environment variables
|
| 186 |
+
export QDRANT_API_KEY="your_api_key"
|
| 187 |
+
export CLUSTER_URL="https://your-qdrant-cluster"
|
| 188 |
+
export MAX_DOCS=5000 # Upload 5000 chunks (instead of default 1000)
|
| 189 |
+
export CHUNK_SIZE=800 # Larger chunks (instead of default 500)
|
| 190 |
+
export CHUNK_OVERLAP=100 # More overlap (instead of default 50)
|
| 191 |
+
|
| 192 |
+
# Run ingestion
|
| 193 |
+
python upload_to_qdrant.py
|
| 194 |
+
```
|
| 195 |
+
|
| 196 |
+
## Monitoring & Tuning
|
| 197 |
+
|
| 198 |
+
When running uploads, watch for:
|
| 199 |
+
|
| 200 |
+
```
|
| 201 |
+
[DEBUG] {title}: {N} pages, {M:,} chars
|
| 202 |
+
```
|
| 203 |
+
|
| 204 |
+
**If chunks seem too large:**
|
| 205 |
+
- Reduce `CHUNK_SIZE` (e.g., 300β400) for more granular retrieval
|
| 206 |
+
- Increases total chunks and computation time
|
| 207 |
+
|
| 208 |
+
**If chunks seem too small:**
|
| 209 |
+
- Increase `CHUNK_SIZE` (e.g., 700β1000) for broader context
|
| 210 |
+
- Reduces total chunks but may lose fine-grained retrieval
|
| 211 |
+
|
| 212 |
+
**If retrieval is imprecise:**
|
| 213 |
+
- Increase `CHUNK_OVERLAP` to 100β150 for richer context overlap
|
| 214 |
+
- Improves recall at small storage cost
|
| 215 |
+
|
| 216 |
+
## Summary
|
| 217 |
+
|
| 218 |
+
This chunking strategy balances:
|
| 219 |
+
- **Semantic coherence** (hierarchical boundaries)
|
| 220 |
+
- **Retrieval accuracy** (overlap for context)
|
| 221 |
+
- **Practical efficiency** (reasonable batch sizes)
|
| 222 |
+
- **Legal precision** (metadata for exact citations)
|
| 223 |
+
|
| 224 |
+
The result is chunks that embeddings models can meaningfully represent, and that users can trace back to exact contract locations.
|
cuad-demo-quadrant/upload_to_qdrant.py
ADDED
|
@@ -0,0 +1,350 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# %% Imports & docstring
|
| 2 |
+
"""
|
| 3 |
+
upload_to_qdrant.py
|
| 4 |
+
βββββββββββββββββββ
|
| 5 |
+
Extracts text from CUAD PDF contracts, generates embeddings with
|
| 6 |
+
all-MiniLM-L6-v2, and uploads up to 1 000 chunks to a Qdrant Cloud
|
| 7 |
+
collection named 'cuad_contracts'.
|
| 8 |
+
|
| 9 |
+
Reuses the PDF extraction and chunking logic from:
|
| 10 |
+
project1/open_search_tuning/cuad_opensearch/notebooks/extract_index_cuad_pdfs.py
|
| 11 |
+
|
| 12 |
+
Usage
|
| 13 |
+
βββββ
|
| 14 |
+
python upload_to_qdrant.py
|
| 15 |
+
|
| 16 |
+
Environment (loaded from .env in this directory)
|
| 17 |
+
βββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 18 |
+
QDRANT_API_KEY β Qdrant Cloud API key
|
| 19 |
+
CLUSTER_URL β Qdrant Cloud cluster URL (without port)
|
| 20 |
+
|
| 21 |
+
Optional env vars
|
| 22 |
+
βββββββββββββββββ
|
| 23 |
+
MAX_DOCS β max chunks to upload (default: 1000)
|
| 24 |
+
CHUNK_SIZE β characters per chunk (default: 500)
|
| 25 |
+
CHUNK_OVERLAP β overlap between chunks (default: 50)
|
| 26 |
+
ENCODE_BATCH_SIZEβ embedding batch size (default: 32)
|
| 27 |
+
UPLOAD_BATCH_SIZEβ upsert batch size (default: 100)
|
| 28 |
+
"""
|
| 29 |
+
|
| 30 |
+
import os
|
| 31 |
+
import sys
|
| 32 |
+
import uuid
|
| 33 |
+
from pathlib import Path
|
| 34 |
+
|
| 35 |
+
from dotenv import load_dotenv
|
| 36 |
+
from sentence_transformers import SentenceTransformer
|
| 37 |
+
from qdrant_client import QdrantClient
|
| 38 |
+
from qdrant_client.models import Distance, VectorParams, PointStruct
|
| 39 |
+
from tqdm import tqdm
|
| 40 |
+
|
| 41 |
+
print("[INFO] Imports loaded successfully.")
|
| 42 |
+
|
| 43 |
+
# %% Configuration β load .env and set constants
|
| 44 |
+
load_dotenv(Path(__file__).resolve().parent / ".env")
|
| 45 |
+
|
| 46 |
+
QDRANT_API_KEY = os.environ["QDRANT_API_KEY"]
|
| 47 |
+
CLUSTER_URL = os.environ["CLUSTER_URL"].strip()
|
| 48 |
+
|
| 49 |
+
COLLECTION_NAME = "cuad_contracts"
|
| 50 |
+
VECTOR_SIZE = 384 # all-MiniLM-L6-v2
|
| 51 |
+
|
| 52 |
+
MAX_DOCS = int(os.getenv("MAX_DOCS", "1000"))
|
| 53 |
+
CHUNK_SIZE = int(os.getenv("CHUNK_SIZE", "500"))
|
| 54 |
+
CHUNK_OVERLAP = int(os.getenv("CHUNK_OVERLAP", "50"))
|
| 55 |
+
ENCODE_BATCH_SIZE = int(os.getenv("ENCODE_BATCH_SIZE", "32"))
|
| 56 |
+
UPLOAD_BATCH_SIZE = int(os.getenv("UPLOAD_BATCH_SIZE", "100"))
|
| 57 |
+
|
| 58 |
+
PDF_ROOT = Path(
|
| 59 |
+
"/home/ridhi/projects/project1/open_search_tuning"
|
| 60 |
+
"/cuad_opensearch/cuad_data/CUAD_v1/full_contract_pdf"
|
| 61 |
+
)
|
| 62 |
+
|
| 63 |
+
print(f"[INFO] Config loaded:")
|
| 64 |
+
print(f" CLUSTER_URL = {CLUSTER_URL}")
|
| 65 |
+
print(f" COLLECTION_NAME = {COLLECTION_NAME}")
|
| 66 |
+
print(f" VECTOR_SIZE = {VECTOR_SIZE}")
|
| 67 |
+
print(f" MAX_DOCS = {MAX_DOCS}")
|
| 68 |
+
print(f" CHUNK_SIZE = {CHUNK_SIZE} | CHUNK_OVERLAP = {CHUNK_OVERLAP}")
|
| 69 |
+
print(f" ENCODE_BATCH_SIZE= {ENCODE_BATCH_SIZE} | UPLOAD_BATCH_SIZE = {UPLOAD_BATCH_SIZE}")
|
| 70 |
+
print(f" PDF_ROOT exists = {PDF_ROOT.exists()}")
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
# %% PDF extraction backend β auto-selects best available library
|
| 74 |
+
def _make_extractor():
|
| 75 |
+
try:
|
| 76 |
+
import fitz
|
| 77 |
+
|
| 78 |
+
def _extract(path: Path):
|
| 79 |
+
pages = []
|
| 80 |
+
with fitz.open(str(path)) as doc:
|
| 81 |
+
for i, page in enumerate(doc):
|
| 82 |
+
pages.append({"page": i + 1, "text": page.get_text("text") or ""})
|
| 83 |
+
return pages
|
| 84 |
+
|
| 85 |
+
print("[DEBUG] PDF backend selected: pymupdf (fitz)")
|
| 86 |
+
return "pymupdf", _extract
|
| 87 |
+
except ImportError:
|
| 88 |
+
print("[DEBUG] pymupdf not available, trying pdfplumber β¦")
|
| 89 |
+
|
| 90 |
+
try:
|
| 91 |
+
import pdfplumber
|
| 92 |
+
|
| 93 |
+
def _extract(path: Path):
|
| 94 |
+
pages = []
|
| 95 |
+
with pdfplumber.open(str(path)) as pdf:
|
| 96 |
+
for i, page in enumerate(pdf.pages):
|
| 97 |
+
pages.append({"page": i + 1, "text": page.extract_text() or ""})
|
| 98 |
+
return pages
|
| 99 |
+
|
| 100 |
+
print("[DEBUG] PDF backend selected: pdfplumber")
|
| 101 |
+
return "pdfplumber", _extract
|
| 102 |
+
except ImportError:
|
| 103 |
+
print("[DEBUG] pdfplumber not available, trying pdfminer β¦")
|
| 104 |
+
|
| 105 |
+
try:
|
| 106 |
+
from pdfminer.high_level import extract_pages
|
| 107 |
+
from pdfminer.layout import LTTextContainer
|
| 108 |
+
|
| 109 |
+
def _extract(path: Path):
|
| 110 |
+
pages = []
|
| 111 |
+
for i, layout in enumerate(extract_pages(str(path))):
|
| 112 |
+
text = "".join(
|
| 113 |
+
el.get_text()
|
| 114 |
+
for el in layout
|
| 115 |
+
if isinstance(el, LTTextContainer)
|
| 116 |
+
)
|
| 117 |
+
pages.append({"page": i + 1, "text": text})
|
| 118 |
+
return pages
|
| 119 |
+
|
| 120 |
+
print("[DEBUG] PDF backend selected: pdfminer")
|
| 121 |
+
return "pdfminer", _extract
|
| 122 |
+
except ImportError:
|
| 123 |
+
pass
|
| 124 |
+
|
| 125 |
+
raise RuntimeError("No PDF library found. Install pymupdf, pdfplumber, or pdfminer.six.")
|
| 126 |
+
|
| 127 |
+
|
| 128 |
+
EXTRACTOR_NAME, extract_pages_from_pdf = _make_extractor()
|
| 129 |
+
print(f"[INFO] PDF extractor : {EXTRACTOR_NAME}")
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
# %% Text chunking helpers
|
| 133 |
+
def split_text_with_offsets(text: str, chunk_size: int, chunk_overlap: int) -> list[dict]:
|
| 134 |
+
separators = ["\n\n", "\n", " ", ""]
|
| 135 |
+
chunks: list[dict] = []
|
| 136 |
+
start = 0
|
| 137 |
+
while start < len(text):
|
| 138 |
+
end = min(start + chunk_size, len(text))
|
| 139 |
+
chunk_text = text[start:end]
|
| 140 |
+
if end < len(text):
|
| 141 |
+
split_at = -1
|
| 142 |
+
for sep in separators:
|
| 143 |
+
idx = chunk_text.rfind(sep)
|
| 144 |
+
if idx > chunk_size // 2:
|
| 145 |
+
split_at = idx + len(sep)
|
| 146 |
+
break
|
| 147 |
+
if split_at > 0:
|
| 148 |
+
end = start + split_at
|
| 149 |
+
chunk_text = text[start:end]
|
| 150 |
+
chunks.append({"text": chunk_text, "char_start": start, "char_end": end})
|
| 151 |
+
if end >= len(text):
|
| 152 |
+
break
|
| 153 |
+
next_start = end - chunk_overlap
|
| 154 |
+
if next_start <= start:
|
| 155 |
+
next_start = start + 1
|
| 156 |
+
start = next_start
|
| 157 |
+
return chunks
|
| 158 |
+
|
| 159 |
+
|
| 160 |
+
# ββ Page-boundary helpers ββββββββββββββββββββββββββββββββββββββββββββββββββββ
|
| 161 |
+
def build_page_map(pages: list[dict]) -> list[tuple[int, int, int]]:
|
| 162 |
+
page_map = []
|
| 163 |
+
pos = 0
|
| 164 |
+
for p in pages:
|
| 165 |
+
end = pos + len(p["text"])
|
| 166 |
+
page_map.append((pos, end, p["page"]))
|
| 167 |
+
pos = end + 2
|
| 168 |
+
return page_map
|
| 169 |
+
|
| 170 |
+
|
| 171 |
+
def char_range_to_pages(char_start: int, char_end: int, page_map: list) -> tuple[int, int]:
|
| 172 |
+
first = last = None
|
| 173 |
+
for seg_start, seg_end, pg in page_map:
|
| 174 |
+
if char_end <= seg_start:
|
| 175 |
+
break
|
| 176 |
+
if char_start < seg_end:
|
| 177 |
+
if first is None:
|
| 178 |
+
first = pg
|
| 179 |
+
last = pg
|
| 180 |
+
return (first or 1, last or 1)
|
| 181 |
+
|
| 182 |
+
|
| 183 |
+
# %% PDF discovery & chunk iterator
|
| 184 |
+
def find_pdfs(root: Path) -> list[Path]:
|
| 185 |
+
return sorted(p for p in root.rglob("*") if p.is_file() and p.suffix.upper() == ".PDF")
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def iter_chunks(all_pdfs: list[Path], limit: int):
|
| 189 |
+
"""Yield chunk dicts until *limit* chunks have been emitted."""
|
| 190 |
+
count = 0
|
| 191 |
+
skipped_pdfs = 0
|
| 192 |
+
for pdf_path in all_pdfs:
|
| 193 |
+
if count >= limit:
|
| 194 |
+
return
|
| 195 |
+
title = pdf_path.stem
|
| 196 |
+
print(f"[DEBUG] Extracting: {pdf_path.name}", end="\r")
|
| 197 |
+
try:
|
| 198 |
+
pages = extract_pages_from_pdf(pdf_path)
|
| 199 |
+
except Exception as exc:
|
| 200 |
+
print(f"\n[WARN] Could not extract {pdf_path.name}: {exc}")
|
| 201 |
+
skipped_pdfs += 1
|
| 202 |
+
continue
|
| 203 |
+
|
| 204 |
+
pages = [p for p in pages if p["text"].strip()]
|
| 205 |
+
if not pages:
|
| 206 |
+
print(f"[WARN] No text extracted from {pdf_path.name} β skipping")
|
| 207 |
+
skipped_pdfs += 1
|
| 208 |
+
continue
|
| 209 |
+
|
| 210 |
+
full_text = "\n\n".join(p["text"] for p in pages)
|
| 211 |
+
page_map = build_page_map(pages)
|
| 212 |
+
rel_path = str(pdf_path.relative_to(PDF_ROOT))
|
| 213 |
+
print(f"[DEBUG] {title}: {len(pages)} pages, {len(full_text):,} chars", end="\r")
|
| 214 |
+
|
| 215 |
+
for chunk_idx, chunk in enumerate(
|
| 216 |
+
split_text_with_offsets(full_text, CHUNK_SIZE, CHUNK_OVERLAP)
|
| 217 |
+
):
|
| 218 |
+
if count >= limit:
|
| 219 |
+
return
|
| 220 |
+
pg_start, pg_end = char_range_to_pages(
|
| 221 |
+
chunk["char_start"], chunk["char_end"], page_map
|
| 222 |
+
)
|
| 223 |
+
yield {
|
| 224 |
+
"doc_id": f"{title}-chunk-{chunk_idx}",
|
| 225 |
+
"title": title,
|
| 226 |
+
"text": chunk["text"],
|
| 227 |
+
"char_start": chunk["char_start"],
|
| 228 |
+
"char_end": chunk["char_end"],
|
| 229 |
+
"page_start": pg_start,
|
| 230 |
+
"page_end": pg_end,
|
| 231 |
+
"pdf_path": rel_path,
|
| 232 |
+
}
|
| 233 |
+
count += 1
|
| 234 |
+
|
| 235 |
+
if skipped_pdfs:
|
| 236 |
+
print(f"\n[INFO] PDFs skipped due to extraction errors: {skipped_pdfs}")
|
| 237 |
+
|
| 238 |
+
|
| 239 |
+
# %% Connect to Qdrant and create collection if needed
|
| 240 |
+
print(f"[INFO] Connecting to Qdrant: {CLUSTER_URL}")
|
| 241 |
+
qdrant = QdrantClient(
|
| 242 |
+
url=f"{CLUSTER_URL}:6333",
|
| 243 |
+
api_key=QDRANT_API_KEY,
|
| 244 |
+
timeout=30, # seconds β avoids silent hangs if cluster is unreachable
|
| 245 |
+
prefer_grpc=False,
|
| 246 |
+
)
|
| 247 |
+
print("[INFO] Qdrant client created.")
|
| 248 |
+
|
| 249 |
+
existing = [c.name for c in qdrant.get_collections().collections]
|
| 250 |
+
print(f"[DEBUG] Existing collections: {existing}")
|
| 251 |
+
if COLLECTION_NAME in existing:
|
| 252 |
+
print(f"[INFO] Collection '{COLLECTION_NAME}' already exists β skipping creation.")
|
| 253 |
+
else:
|
| 254 |
+
qdrant.create_collection(
|
| 255 |
+
collection_name=COLLECTION_NAME,
|
| 256 |
+
vectors_config=VectorParams(size=VECTOR_SIZE, distance=Distance.COSINE),
|
| 257 |
+
)
|
| 258 |
+
print(f"[INFO] Collection '{COLLECTION_NAME}' created (dim={VECTOR_SIZE}, distance=Cosine).")
|
| 259 |
+
|
| 260 |
+
|
| 261 |
+
# %% Load embedding model
|
| 262 |
+
# NOTE: first run downloads ~90 MB from HuggingFace β this can take a minute.
|
| 263 |
+
# Subsequent runs load from the local cache and are fast.
|
| 264 |
+
print("[INFO] Loading embedding model all-MiniLM-L6-v2 (downloading if not cached) β¦")
|
| 265 |
+
model = SentenceTransformer("all-MiniLM-L6-v2", device="cpu")
|
| 266 |
+
print(f"[INFO] Model loaded. Max sequence length: {model.max_seq_length} tokens.")
|
| 267 |
+
|
| 268 |
+
|
| 269 |
+
# %% Discover PDFs
|
| 270 |
+
all_pdfs = find_pdfs(PDF_ROOT)
|
| 271 |
+
print(f"[INFO] PDFs discovered : {len(all_pdfs)}")
|
| 272 |
+
print(f"[INFO] Target chunks : {MAX_DOCS} | chunk_size={CHUNK_SIZE} overlap={CHUNK_OVERLAP}")
|
| 273 |
+
if not all_pdfs:
|
| 274 |
+
raise FileNotFoundError(f"No PDFs found under {PDF_ROOT}. Check PDF_ROOT path.")
|
| 275 |
+
|
| 276 |
+
# %% Encode & upload in batches
|
| 277 |
+
chunk_buffer: list[dict] = []
|
| 278 |
+
uploaded = 0
|
| 279 |
+
errors = 0
|
| 280 |
+
|
| 281 |
+
def flush_buffer(buf: list[dict]) -> int:
|
| 282 |
+
"""Encode and upsert a batch; returns number of points uploaded."""
|
| 283 |
+
texts = [d["text"] for d in buf]
|
| 284 |
+
print(f"[DEBUG] Encoding batch of {len(texts)} chunks β¦", end="\r")
|
| 285 |
+
embeddings = model.encode(
|
| 286 |
+
texts,
|
| 287 |
+
batch_size=ENCODE_BATCH_SIZE,
|
| 288 |
+
show_progress_bar=False,
|
| 289 |
+
normalize_embeddings=True,
|
| 290 |
+
)
|
| 291 |
+
print(f"[DEBUG] Embeddings shape: {embeddings.shape} β upserting β¦", end="\r")
|
| 292 |
+
points = [
|
| 293 |
+
PointStruct(
|
| 294 |
+
id=str(uuid.uuid5(uuid.NAMESPACE_DNS, d["doc_id"])),
|
| 295 |
+
vector=embeddings[i].tolist(),
|
| 296 |
+
payload={
|
| 297 |
+
"doc_id": d["doc_id"],
|
| 298 |
+
"title": d["title"],
|
| 299 |
+
"text": d["text"],
|
| 300 |
+
"char_start": d["char_start"],
|
| 301 |
+
"char_end": d["char_end"],
|
| 302 |
+
"page_start": d["page_start"],
|
| 303 |
+
"page_end": d["page_end"],
|
| 304 |
+
"pdf_path": d["pdf_path"],
|
| 305 |
+
},
|
| 306 |
+
)
|
| 307 |
+
for i, d in enumerate(buf)
|
| 308 |
+
]
|
| 309 |
+
qdrant.upsert(collection_name=COLLECTION_NAME, points=points)
|
| 310 |
+
return len(points)
|
| 311 |
+
|
| 312 |
+
|
| 313 |
+
with tqdm(total=MAX_DOCS, desc="Uploading chunks", unit="chunk") as pbar:
|
| 314 |
+
for chunk in iter_chunks(all_pdfs, MAX_DOCS):
|
| 315 |
+
chunk_buffer.append(chunk)
|
| 316 |
+
if len(chunk_buffer) >= UPLOAD_BATCH_SIZE:
|
| 317 |
+
try:
|
| 318 |
+
n = flush_buffer(chunk_buffer)
|
| 319 |
+
uploaded += n
|
| 320 |
+
pbar.update(n)
|
| 321 |
+
print(f"[INFO] Batch upserted β total uploaded so far: {uploaded}", end="\r")
|
| 322 |
+
except Exception as exc:
|
| 323 |
+
print(f"\n[ERROR] Upsert failed: {exc}")
|
| 324 |
+
errors += 1
|
| 325 |
+
chunk_buffer.clear()
|
| 326 |
+
|
| 327 |
+
# Flush remainder
|
| 328 |
+
if chunk_buffer:
|
| 329 |
+
print(f"\n[INFO] Flushing final batch of {len(chunk_buffer)} chunks β¦")
|
| 330 |
+
try:
|
| 331 |
+
n = flush_buffer(chunk_buffer)
|
| 332 |
+
uploaded += n
|
| 333 |
+
pbar.update(n)
|
| 334 |
+
except Exception as exc:
|
| 335 |
+
print(f"\n[ERROR] Final upsert failed: {exc}")
|
| 336 |
+
errors += 1
|
| 337 |
+
chunk_buffer.clear()
|
| 338 |
+
|
| 339 |
+
|
| 340 |
+
# %% Summary
|
| 341 |
+
info = qdrant.get_collection(COLLECTION_NAME)
|
| 342 |
+
print("\n====== UPLOAD COMPLETE ======")
|
| 343 |
+
print(f"[INFO] Collection : {COLLECTION_NAME}")
|
| 344 |
+
print(f"[INFO] Chunks uploaded : {uploaded}")
|
| 345 |
+
print(f"[INFO] Errors : {errors}")
|
| 346 |
+
print(f"[INFO] Vectors in coll.: {info.points_count}")
|
| 347 |
+
if errors:
|
| 348 |
+
print(f"[WARN] {errors} batch(es) failed β check [ERROR] lines above.")
|
| 349 |
+
|
| 350 |
+
# %%
|
tests/verify_collection.py
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
"""
|
| 3 |
+
verify_collection.py
|
| 4 |
+
ββββββββββββββββββββ
|
| 5 |
+
Test script to verify that documents are properly uploaded to the Qdrant collection.
|
| 6 |
+
|
| 7 |
+
Connects to the Qdrant cluster and retrieves collection stats and sample documents.
|
| 8 |
+
|
| 9 |
+
Usage
|
| 10 |
+
βββββ
|
| 11 |
+
python tests/verify_collection.py
|
| 12 |
+
"""
|
| 13 |
+
|
| 14 |
+
import os
|
| 15 |
+
import sys
|
| 16 |
+
from pathlib import Path
|
| 17 |
+
|
| 18 |
+
from dotenv import load_dotenv
|
| 19 |
+
from qdrant_client import QdrantClient
|
| 20 |
+
|
| 21 |
+
# Load environment variables from parent directory's .env
|
| 22 |
+
env_path = Path(__file__).resolve().parent.parent / "cuad-demo-quadrant" / ".env"
|
| 23 |
+
load_dotenv(env_path)
|
| 24 |
+
|
| 25 |
+
# Configuration
|
| 26 |
+
QDRANT_API_KEY = os.environ.get("QDRANT_API_KEY")
|
| 27 |
+
CLUSTER_URL = os.environ.get("CLUSTER_URL", "").strip()
|
| 28 |
+
COLLECTION_NAME = "cuad_contracts"
|
| 29 |
+
|
| 30 |
+
if not QDRANT_API_KEY or not CLUSTER_URL:
|
| 31 |
+
print("[ERROR] Missing QDRANT_API_KEY or CLUSTER_URL in .env")
|
| 32 |
+
sys.exit(1)
|
| 33 |
+
|
| 34 |
+
print(f"[INFO] Connecting to Qdrant cluster: {CLUSTER_URL}")
|
| 35 |
+
|
| 36 |
+
try:
|
| 37 |
+
qdrant = QdrantClient(
|
| 38 |
+
url=f"{CLUSTER_URL}:6333",
|
| 39 |
+
api_key=QDRANT_API_KEY,
|
| 40 |
+
timeout=30,
|
| 41 |
+
prefer_grpc=False,
|
| 42 |
+
)
|
| 43 |
+
print("[β] Connected to Qdrant cluster successfully.")
|
| 44 |
+
except Exception as e:
|
| 45 |
+
print(f"[ERROR] Failed to connect: {e}")
|
| 46 |
+
sys.exit(1)
|
| 47 |
+
|
| 48 |
+
# Get collection info
|
| 49 |
+
print(f"\n[INFO] Retrieving collection '{COLLECTION_NAME}' info...")
|
| 50 |
+
try:
|
| 51 |
+
info = qdrant.get_collection(COLLECTION_NAME)
|
| 52 |
+
print(f"[β] Collection found.")
|
| 53 |
+
print(f" Points count : {info.points_count}")
|
| 54 |
+
print(f" Vector size : {info.config.vectors_config.size if hasattr(info.config, 'vectors_config') else 'N/A'}")
|
| 55 |
+
except Exception as e:
|
| 56 |
+
print(f"[ERROR] Failed to get collection info: {e}")
|
| 57 |
+
sys.exit(1)
|
| 58 |
+
|
| 59 |
+
# List all collections
|
| 60 |
+
print(f"\n[INFO] Available collections:")
|
| 61 |
+
try:
|
| 62 |
+
collections = qdrant.get_collections().collections
|
| 63 |
+
for coll in collections:
|
| 64 |
+
print(f" - {coll.name}")
|
| 65 |
+
except Exception as e:
|
| 66 |
+
print(f"[ERROR] Failed to list collections: {e}")
|
| 67 |
+
|
| 68 |
+
# Retrieve and display sample documents
|
| 69 |
+
print(f"\n[INFO] Retrieving sample documents...")
|
| 70 |
+
try:
|
| 71 |
+
# Scroll through the collection to get sample points
|
| 72 |
+
points, next_page_offset = qdrant.scroll(
|
| 73 |
+
collection_name=COLLECTION_NAME,
|
| 74 |
+
limit=5,
|
| 75 |
+
with_payload=True,
|
| 76 |
+
with_vectors=False,
|
| 77 |
+
)
|
| 78 |
+
|
| 79 |
+
if not points:
|
| 80 |
+
print("[WARN] No points found in collection!")
|
| 81 |
+
else:
|
| 82 |
+
print(f"[β] Retrieved {len(points)} sample documents:\n")
|
| 83 |
+
for i, point in enumerate(points, 1):
|
| 84 |
+
payload = point.payload
|
| 85 |
+
print(f" [{i}] ID: {point.id}")
|
| 86 |
+
print(f" Doc ID : {payload.get('doc_id', 'N/A')}")
|
| 87 |
+
print(f" Title : {payload.get('title', 'N/A')}")
|
| 88 |
+
print(f" PDF Path : {payload.get('pdf_path', 'N/A')}")
|
| 89 |
+
print(f" Pages : {payload.get('page_start', 'N/A')}-{payload.get('page_end', 'N/A')}")
|
| 90 |
+
text_preview = payload.get('text', '')[:100].replace('\n', ' ')
|
| 91 |
+
print(f" Text : {text_preview}...")
|
| 92 |
+
print()
|
| 93 |
+
except Exception as e:
|
| 94 |
+
print(f"[ERROR] Failed to retrieve documents: {e}")
|
| 95 |
+
sys.exit(1)
|
| 96 |
+
|
| 97 |
+
print("[β] Verification complete!")
|
| 98 |
+
print(f"\n[INFO] Summary:")
|
| 99 |
+
print(f" Collection: {COLLECTION_NAME}")
|
| 100 |
+
print(f" Total uploaded documents: {info.points_count}")
|