Spaces:
Running
Running
Commit
·
aac482c
1
Parent(s):
452ed79
matched_species_i fixed but only less number of tags issue remainign while db creation
Browse files- retrieval_evaluation.py +10 -0
retrieval_evaluation.py
CHANGED
|
@@ -268,6 +268,16 @@ def main():
|
|
| 268 |
print(f" - Sample species: {species_field}")
|
| 269 |
print(f" - Sample region: {region_field}")
|
| 270 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 271 |
# Step 2: Generate questions for chunks
|
| 272 |
print("\n2. Generating questions from chunks...")
|
| 273 |
question_generator = QuestionGenerator()
|
|
|
|
| 268 |
print(f" - Sample species: {species_field}")
|
| 269 |
print(f" - Sample region: {region_field}")
|
| 270 |
|
| 271 |
+
##### DEBUGGING: Print all species and region values #####
|
| 272 |
+
print("\n##### ALL CHUNK METADATA DEBUG #####")
|
| 273 |
+
for i, chunk in enumerate(chunks):
|
| 274 |
+
metadata = chunk['metadata']
|
| 275 |
+
species = metadata.get('matched_specie_0', 'MISSING')
|
| 276 |
+
region = metadata.get('region', 'MISSING')
|
| 277 |
+
source = metadata.get('source', 'unknown')[:50] + "..." # Truncate for readability
|
| 278 |
+
print(f"Chunk {i+1:2d}: Species='{species}' | Region='{region}' | Source={source}")
|
| 279 |
+
print("##### END DEBUG #####\n")
|
| 280 |
+
|
| 281 |
# Step 2: Generate questions for chunks
|
| 282 |
print("\n2. Generating questions from chunks...")
|
| 283 |
question_generator = QuestionGenerator()
|