Jeff Gardner
|
1ecb5c9f96
Fix QMD_LLAMA_GPU backend override handling
|
vor 1 Monat |
JohnRichardEnders
|
50ce17bbfa
feat(llm): resolve models as config > env > default
|
vor 1 Monat |
Tobi Lutke
|
55f16460d0
fix(ci): guard LLM calls in CI and increase test timeouts
|
vor 2 Monaten |
Tobi Lutke
|
e3549dab1a
perf(rerank): cap parallelism, deduplicate chunks, cache by content
|
vor 2 Monaten |
Brian Le
|
0dec1df047
fix(llm): make expansion context size configurable
|
vor 2 Monaten |
Tobi Lütke
|
5233e676d9
fix(rerank): truncate documents exceeding 2048-token context size
|
vor 3 Monaten |
Tobi Lutke
|
870d3aed3b
test: move all tests to flat test/ directory
|
vor 3 Monaten |