diff options
| author | Gustaf Rydholm <gustaf.rydholm@gmail.com> | 2024-05-29 00:53:39 +0200 |
|---|---|---|
| committer | Gustaf Rydholm <gustaf.rydholm@gmail.com> | 2024-05-29 00:53:39 +0200 |
| commit | 716e3fe58adee5b8a6bfa91de4b3ba6cf204d172 (patch) | |
| tree | 778da9011d21051006fc206ce0978f0fc114b77b /README.md | |
| parent | 2d91c118d71a8dd7fbd7f9cf21f86e92da33827e (diff) | |
Wip memory
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 6 |
1 files changed, 6 insertions, 0 deletions
@@ -98,6 +98,12 @@ streamlit run rag/ui.py Yes, it is inefficient/dumb to use ollama when you can just load the models with python in the same process. +### TODO + +-[ ] Rerank history if it is relevant. +-[ ] message ollama/cohere +-[ ] create db script + ### Inspiration I took some inspiration from these tutorials: |