Improve performance with contextual compression, a technique where retrieved documents are compressed, and irrelevant information is filtered out. 9caad80 vinhnx90 commited on Apr 2
Disable tokenizer transformer parallelism to avoid deadlocks 91d4c2f unverified Vinh Nguyen commited on Apr 2
Use all-mpnet-base-v2 vector embedding for highest performance 1ec5b20 unverified Vinh Nguyen commited on Apr 2