Commit Graph

74 Commits (87cc3cf168a646b449ba749aa79f131013990ef8)

Author SHA1 Message Date
Pavel d57c7b0296 -y-description 1 year ago
冯不游 b83589a308 feat: add support for directory list
example: `python ingest.py --dir inputs1 --dir another --dir ../inputs`,
the outputs will be in `outputs/input_folder_name/`
1 year ago
Alex d4ede13747 Merge branch 'main' into code-ingestion 1 year ago
Alex 5883ce2685
Merge pull request #87 from arc53/ingest-cli
Ingest cli
1 year ago
Pavel af20c7298a new-ingest
Ingest with a CLI
1 year ago
冯不游 636783ca8a fix: avoid second error issue 1 year ago
冯不游 458f2a3ff3 fix: restore index back when continue process 1 year ago
Alex 046fbebf56 Enable other llm's 1 year ago
冯不游 3ab02ca959 feat: compatible with markdown 1 year ago
Alex e88ff885fe
Merge pull request #75 from arc53/rst-interpreters 1 year ago
Pavel b1a6ebffba Directives + Interpreted
Some additional filters for rst parsing
1 year ago
Alex 205be538a3 fix dbqa, with new chain type, also fix for doc export 1 year ago
Alex 9228005a7e chunked embedding 1 year ago
vintro 2a203aa547
Create __init__.py
otherwise running `python ingest.py` complains about `parser` not being a package
1 year ago
Alex 37ad3b35c8 Update ingest.py 1 year ago
Alex d642782a5a move folder 1 year ago
Pavel 8c4fcff617 requirement 1 year ago
Pavel 79b5ef9c14 Bulk ingest
Added a method based on indexGPT folder ingester. Additional rst reader included.
1 year ago
Alex 605c599b5d Create code_docs_gen.py 1 year ago
Patrick Shriwise 64fb36b3de Adding location argument to ingest scripts 1 year ago
Alex 08215248d7 Inputs folder change 1 year ago
monkish54 c94866e9e9 Add cost estimate feature
Calculates number of tokens/user cost and requires user permission to proceed.

User permission bypass is built-in to allow for non-human users.
1 year ago
Pavel 1c734727a1 Ingest rst with sphinx
Transforms all rst files in provided folder to txt format first (utilising sphinx library). In my tests size of raw sample decreased 2-3 times.
1 year ago
Alex b71a9bf5ee init2 1 year ago