gutendex processing implementation

This commit is contained in:
Doar Mihai
2026-03-29 15:23:02 +03:00
parent 7be6af781b
commit 93fef1512a
7 changed files with 542 additions and 0 deletions
+30
View File
@@ -63,3 +63,33 @@ AWS_BUCKET=
AWS_USE_PATH_STYLE_ENDPOINT=false
VITE_APP_NAME="${APP_NAME}"
# Gutendex Configuration
GUTENDEX_API_URL=https://gutendex.com
GUTENDEX_DEFAULT_LANGUAGE=en
GUTENDEX_BATCH_SIZE=50
GUTENDEX_RATE_LIMIT_DELAY=1000
GUTENDEX_TIMEOUT=30
GUTENDEX_RETRY_MAX_ATTEMPTS=3
GUTENDEX_RETRY_BACKOFF=2
GUTENDEX_COPYRIGHT_FILTER=false
GUTENDEX_CACHE_ENABLED=true
GUTENDEX_CACHE_TTL=86400
# Ollama Configuration
OLLAMA_API_URL=http://localhost:11434
OLLAMA_MODEL=llama3
OLLAMA_TIMEOUT=300
OLLAMA_MAX_TOKENS=4000
OLLAMA_TEMPERATURE=0.3
OLLAMA_RETRY_MAX_ATTEMPTS=3
OLLAMA_RETRY_BACKOFF=5
OLLAMA_TEXT_MAX_LENGTH=50000
OLLAMA_TEXT_STRATEGY=beginning
OLLAMA_MIN_WORD_COUNT=100
OLLAMA_MAX_WORD_COUNT=1000
OLLAMA_MIN_SENTENCE_COUNT=5
OLLAMA_NUM_PREDICT=1000
OLLAMA_TOP_K=40
OLLAMA_TOP_P=0.9
OLLAMA_REPEAT_PENALTY=1.1