error.log

2026-07-23 16:20:48,573 ERROR    Learn2RAGImporter process_delta_imports: error processing loader '4315d1c1-db3d-4a0b-a8f3-06a879981361': 'utf-8' codec can't encode characters in position 1226-1227: surrogates not allowed
Traceback (most recent call last):
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/importer/loaders/process_loaders.py", line 352, in process_delta_imports
    index(all_docs, user_config, opt_config)
    ~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/pipeline/ingestion.py", line 233, in index
    ingest_batch(documents, qdrant, user_config, opt_config)
    ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/pipeline/ingestion.py", line 152, in ingest_batch
    chunk_hash = [hashlib.md5(chunk.page_content.encode()).hexdigest() for chunk in chunks]
                              ~~~~~~~~~~~~~~~~~~~~~~~~~^^
UnicodeEncodeError: 'utf-8' codec can't encode characters in position 1226-1227: surrogates not allowed
2026-07-23 16:28:17,181 ERROR    Learn2RAGImporter process_delta_imports: error processing loader '4315d1c1-db3d-4a0b-a8f3-06a879981361': 'utf-8' codec can't encode characters in position 1226-1227: surrogates not allowed
Traceback (most recent call last):
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/importer/loaders/process_loaders.py", line 352, in process_delta_imports
    index(all_docs, user_config, opt_config)
    ~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/pipeline/ingestion.py", line 233, in index
    ingest_batch(documents, qdrant, user_config, opt_config)
    ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/pipeline/ingestion.py", line 152, in ingest_batch
    chunk_hash = [hashlib.md5(chunk.page_content.encode()).hexdigest() for chunk in chunks]
                              ~~~~~~~~~~~~~~~~~~~~~~~~~^^
UnicodeEncodeError: 'utf-8' codec can't encode characters in position 1226-1227: surrogates not allowed
2026-07-23 16:34:14,329 ERROR    Learn2RAGImporter process_delta_imports: error processing loader '4315d1c1-db3d-4a0b-a8f3-06a879981361': 'utf-8' codec can't encode characters in position 1226-1227: surrogates not allowed
Traceback (most recent call last):
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/importer/loaders/process_loaders.py", line 352, in process_delta_imports
    index(all_docs, user_config, opt_config)
    ~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/pipeline/ingestion.py", line 233, in index
    ingest_batch(documents, qdrant, user_config, opt_config)
    ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/pipeline/ingestion.py", line 152, in ingest_batch
    chunk_hash = [hashlib.md5(chunk.page_content.encode()).hexdigest() for chunk in chunks]
                              ~~~~~~~~~~~~~~~~~~~~~~~~~^^
UnicodeEncodeError: 'utf-8' codec can't encode characters in position 1226-1227: surrogates not allowed
2026-07-24 07:43:02,814 ERROR    Learn2RAGImporter process_delta_imports: error processing loader '4315d1c1-db3d-4a0b-a8f3-06a879981361': 'utf-8' codec can't encode characters in position 1226-1227: surrogates not allowed
Traceback (most recent call last):
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/importer/loaders/process_loaders.py", line 352, in process_delta_imports
    index(all_docs, user_config, opt_config)
    ~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/pipeline/ingestion.py", line 233, in index
    ingest_batch(documents, qdrant, user_config, opt_config)
    ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.local/share/pyapp/learn2rag/12921567730362251138/0.3.0/lib/python3.13/site-packages/learn2rag/pipeline/ingestion.py", line 152, in ingest_batch
    chunk_hash = [hashlib.md5(chunk.page_content.encode()).hexdigest() for chunk in chunks]
                              ~~~~~~~~~~~~~~~~~~~~~~~~~^^
UnicodeEncodeError: 'utf-8' codec can't encode characters in position 1226-1227: surrogates not allowed