Yiorgis Gozadinos 4b2dfcd72f Use an LLM to evaluate adequacy of simple Q/A and if inadequate escalate to deep Q/A		2025-10-13 18:01:23 +03:00
..
embeddings	Return an empty array when request en empty embedding	2025-09-30 11:31:50 +03:00
graph	Deep QA multi-agent	2025-09-30 16:59:36 +03:00
qa	We have positional indexing for a while now	2025-10-13 18:01:22 +03:00
reranking	Add option to skip db in evals	2025-09-30 11:31:51 +03:00
research	Shuffle reusable nodes under graph/	2025-09-30 16:59:36 +03:00
store	Make sure vacuum task has been complete before exiting the client	2025-10-07 12:27:55 +03:00
__init__.py	init repo	2025-06-15 13:21:17 +02:00
a2a.py	Use an LLM to evaluate adequacy of simple Q/A and if inadequate escalate to deep Q/A	2025-10-13 18:01:23 +03:00
app.py	Rename nodes to make it clear they are part of Q/A	2025-09-30 16:59:36 +03:00
chunker.py	Operate on DoclingDocument instead of Document	2025-08-08 17:24:34 +02:00
cli.py	Remove alternative a2a options, there will only one	2025-10-13 18:01:21 +03:00
client.py	Make it possible to override the QA agent system prompt using the client	2025-10-07 13:15:58 +03:00
config.py	Implement an LRUMemoryStorage for context	2025-10-13 18:01:22 +03:00
logging.py	Suppress warnings in cli	2025-09-10 13:36:12 +03:00
mcp.py	Add ask, research as tools to mcp	2025-10-08 09:13:21 +03:00
migration.py	Centralize vacuuming	2025-10-07 12:05:25 +03:00
monitor.py	When rebuilding if a document does not exist anymore, re-embed the chunks instead of failing	2025-09-30 16:57:02 +03:00
reader.py	AsciiDoc uses .adoc, not just .asciidoc extensions	2025-09-25 10:09:21 +03:00
utils.py	CLI command to prefetch models (Ollama & Docling)	2025-09-23 16:30:56 +03:00