| -rw-r--r-- | .gitignore | 10L |
| -rw-r--r-- | embeddings/ai_detection/process.py | 35L |
| -rw-r--r-- | embeddings/ai_detection/train.py | 29L |
| -rw-r--r-- | embeddings/docs/index.py | 44L |
| -rw-r--r-- | embeddings/docs/similarity.py | 39L |
| -rw-r--r-- | llm-search/CMakeLists.txt | 25L |
| -rw-r--r-- | llm-search/include/nlohmann/json.hpp | 24640L |
| -rw-r--r-- | llm-search/include/openai.hpp | 1119L |
| -rw-r--r-- | llm-search/src/main.cpp | 195L |
| -rw-r--r-- | llm-search/src/prompts.cpp | 55L |
| -rw-r--r-- | nli/nli-test.py | 82L |
| -rw-r--r-- | search-engine-postgres/Makefile | 3L |
| -rw-r--r-- | search-engine-postgres/TODO.md | 21L |
| -rw-r--r-- | search-engine-postgres/crawling/README.md | 13L |
| -rw-r--r-- | search-engine-postgres/crawling/__init__.py | 0B |
| -rw-r--r-- | search-engine-postgres/crawling/__pycache__/__init__.cpython-313.pyc | 161B |
| -rw-r--r-- | search-engine-postgres/crawling/__pycache__/clean_cache.cpython-313.pyc | 2680B |
| -rw-r--r-- | search-engine-postgres/crawling/__pycache__/constants.cpython-313.pyc | 427B |
| -rw-r--r-- | search-engine-postgres/crawling/__pycache__/spider.cpython-313.pyc | 16965B |
| -rw-r--r-- | search-engine-postgres/crawling/clean.py | 32L |
| -rw-r--r-- | search-engine-postgres/crawling/clean_cache.py | 58L |
| -rw-r--r-- | search-engine-postgres/crawling/constants.py | 8L |
| -rw-r--r-- | search-engine-postgres/crawling/spider.py | 474L |
| -rw-r--r-- | search-engine-postgres/indexing/README.md | 51L |
| -rw-r--r-- | search-engine-postgres/indexing/__init__.py | 0B |
| -rw-r--r-- | search-engine-postgres/indexing/__pycache__/__init__.cpython-313.pyc | 161B |
| -rw-r--r-- | search-engine-postgres/indexing/__pycache__/clean.cpython-313.pyc | 682B |
| -rw-r--r-- | search-engine-postgres/indexing/__pycache__/page_parsing.cpython-313.pyc | 13616B |
| -rw-r--r-- | search-engine-postgres/indexing/__pycache__/terms.cpython-313.pyc | 2783B |
| -rw-r--r-- | search-engine-postgres/indexing/__pycache__/utils.cpython-313.pyc | 3335B |
| -rw-r--r-- | search-engine-postgres/indexing/clean.py | 17L |
| -rw-r--r-- | search-engine-postgres/indexing/page_parsing.py | 386L |
| -rw-r--r-- | search-engine-postgres/indexing/utils.py | 79L |
| -rwxr-xr-x | search-engine-postgres/run.sh | 11L |
| -rw-r--r-- | search-engine-postgres/search/__pycache__/query.cpython-313.pyc | 3855B |
| -rw-r--r-- | search-engine-postgres/search/query.py | 108L |
| -rw-r--r-- | search-engine-postgres/seeds/code.txt | 3L |
| -rw-r--r-- | search-engine-postgres/seeds/dictionaries.txt | 4L |
| -rw-r--r-- | search-engine-postgres/seeds/music.txt | 5L |
| -rw-r--r-- | search-engine-postgres/seeds/otr.txt | 8L |
| -rw-r--r-- | search-engine-postgres/seeds/piracy.txt | 6L |
| -rw-r--r-- | search-engine-postgres/seeds/research.txt | 7L |
| -rw-r--r-- | search-engine-postgres/seeds/wikis.txt | 6L |
| -rwxr-xr-x | search-engine-postgres/setup.sh | 12L |
| -rw-r--r-- | smol/web/__pycache__/web_search.cpython-313.pyc | 5299B |
| -rw-r--r-- | smol/web/search.py | 72L |
| -rw-r--r-- | smol/web/web_search.py | 84L |
| -rw-r--r-- | sqlite-tfidf/TODO.md | 186L |
| -rw-r--r-- | sqlite-tfidf/collection/__pycache__/prune.cpython-313.pyc | 1740B |
| -rw-r--r-- | sqlite-tfidf/collection/prune.py | 35L |
| -rw-r--r-- | sqlite-tfidf/collection/spider.py | 256L |
| -rw-r--r-- | sqlite-tfidf/indexing/__init__.py | 0B |
| -rw-r--r-- | sqlite-tfidf/indexing/__pycache__/__init__.cpython-313.pyc | 161B |
| -rw-r--r-- | sqlite-tfidf/indexing/__pycache__/utils.cpython-313.pyc | 5219B |
| -rw-r--r-- | sqlite-tfidf/indexing/idf.py | 22L |
| -rw-r--r-- | sqlite-tfidf/indexing/lang-detect.py | 41L |
| -rw-r--r-- | sqlite-tfidf/indexing/tf.py | 43L |
| -rw-r--r-- | sqlite-tfidf/indexing/utils.py | 123L |
| -rw-r--r-- | sqlite-tfidf/metrics/cosine-similarity.py | 26L |
| -rw-r--r-- | sqlite-tfidf/metrics/tf-idf.py | 121L |
| -rw-r--r-- | sqlite-tfidf/pyproject.toml | 8L |
| -rw-r--r-- | sqlite-tfidf/search/query.py | 54L |
| -rw-r--r-- | sqlite-tfidf/seeds/code.txt | 7L |
| -rw-r--r-- | sqlite-tfidf/seeds/dictionaries.txt | 4L |
| -rw-r--r-- | sqlite-tfidf/seeds/music.txt | 5L |
| -rw-r--r-- | sqlite-tfidf/seeds/otr.txt | 8L |
| -rw-r--r-- | sqlite-tfidf/seeds/piracy.txt | 6L |
| -rw-r--r-- | sqlite-tfidf/seeds/research.txt | 7L |
| -rw-r--r-- | sqlite-tfidf/seeds/wikis.txt | 6L |
| -rw-r--r-- | web-research/CMakeLists.txt | 28L |
| -rw-r--r-- | web-research/include/nlohmann/json.hpp | 24640L |
| -rw-r--r-- | web-research/include/openai.hpp | 1119L |
| -rw-r--r-- | web-research/include/researcher.hpp | 23L |
| -rw-r--r-- | web-research/src/main.cpp | 78L |
| -rw-r--r-- | web-research/src/researcher.cpp | 186L |
| -rw-r--r-- | web-research/src/summary.cpp | 59L |