24 lines
623 B
Plaintext
24 lines
623 B
Plaintext
---Read File Tool for Retrieve Agent---
|
|
|
|
---Easy Config of system prompts---
|
|
examples into prompts & better prompts
|
|
|
|
---LMS CLI script to load multiple models and to make each model accept multiple inferences---
|
|
|
|
---context engineering, - only include vector hits that are x distance? --- top 5 is good enough
|
|
|
|
AI in the middle - make the ai generate the string for vector search
|
|
|
|
instruction tuned embeddings?
|
|
|
|
entity chunking & re-ranking
|
|
|
|
bredth vs depth = separate workflows
|
|
|
|
common model attributes - temp & top-k
|
|
|
|
QA specific embedding models?
|
|
|
|
Evaluation metrics, how good is it doing?
|
|
rate my response!?
|