23 Commits

Author	SHA1	Message	Date
Alex	ed08123550	Add support for setting the number of chunks processed per query	2024-03-22 14:50:56 +00:00
Anton Larin	577556678c	Fix model selection at least for openAI LLM_NAME	2024-03-21 10:14:48 +01:00
Alex	2be523cf77	Fix handling of embeddings_key in api_search() function	2024-01-30 17:22:33 +00:00
Alex	6a70e3e45b	Commented out unused code in api_search function	2024-01-12 14:39:17 +00:00
Alex	a04cdee33f	Refactor source log generation in complete_stream function	2024-01-12 14:38:15 +00:00
Alex	157769eeb4	Add API endpoint for searching documents	2024-01-12 14:35:23 +00:00
Alex	015bc7c8c3	hotfix source doc data	2023-12-22 12:10:35 +00:00
Alex	af1a0c3520	Update routes.py	2023-11-23 11:31:07 +00:00
Alex	b2770f67a1	custom prompts	2023-11-22 23:55:41 +00:00
Alex	852b016111	fix path bug on default	2023-11-17 15:33:51 +00:00
Alex	ba77a67ba7	fix path	2023-11-17 15:31:53 +00:00
Alex	0974085c6f	prompts	2023-11-14 01:16:06 +00:00
Alex	04b4001277	anthropic working	2023-10-28 19:51:12 +01:00
Alex	9a33bf2210	script + cpu optimisations	2023-10-01 19:16:13 +01:00
Alex	6045cbbc62	Merge pull request #355 from arc53/feature/cpu-llm ... llama-cpp local	2023-10-01 17:55:26 +01:00
Alex	9bbf4044e0	script	2023-10-01 17:20:47 +01:00
Alex	94164c2a71	Merge branch 'main' into featue/elasticsearch	2023-09-30 15:30:23 +01:00
Alex	347cfe253f	elastic2	2023-09-29 17:17:48 +01:00
Alex	e4be38b9f7	sagemaker + llm creator class	2023-09-29 01:09:01 +01:00
Alex	852de8bdfc	ruff linting	2023-09-27 18:01:40 +01:00
Alex	8fa9657ba6	working full	2023-09-27 16:25:57 +01:00
Alex	025549ebf8	fixes to make it work	2023-09-26 13:00:17 +01:00
Alex	e85a583f0a	testings	2023-09-26 10:03:22 +01:00