969d25209c
using openailike for llamaindex that will allow of usage of any openai compatible models via api, and not just hardcoded models inside default OpenAI class in llamaindex
2026-03-09 09:59:27 +03:00
6b3fa1cfaa
more sophisticated chat like retrieval for llamaindex
2026-02-26 19:02:05 +03:00
468d5fb572
proper response
2026-02-26 17:29:54 +03:00
2e0a0718cd
proper response
2026-02-26 17:24:15 +03:00
0cef887155
llamaindex cors middleware
2026-02-26 16:33:03 +03:00
c6715eb021
llamaindex server port change
2026-02-26 15:15:02 +03:00
9ec3d9281d
llamaindex requirements.txt
2026-02-26 15:09:30 +03:00
ba1b7abf0a
demo ui now has 3 tabs for each rag OSS solution
2026-02-26 15:05:18 +03:00
3e29ea70ed
langchain uploading new way of predefined paths from yandex disk
2026-02-26 00:01:47 +03:00
2c7ab06b3f
ragflow in the repository, with codex-created yandex disk plugin JUST IN CASE, also llamaindex enrichment with yandex disk predefined data
2026-02-25 11:28:29 +03:00
c29928cc89
prefect flow and task working inside langchain project
2026-02-16 16:04:47 +03:00
77c578c9e6
Prefect client prep for langchain
2026-02-16 15:12:44 +03:00
93d538ecc6
Checking properly source of the file for metadata, with instanceof
2026-02-11 16:23:27 +03:00
f5659675ec
- main feat: adaptation for async enrichment
...
- added file_type, this will hold the "таблица", "презентация" and so on types
- file source metadata is now taken either from local source or yandex disk.
2026-02-11 15:46:54 +03:00
7b52887558
Enrichment now processed via chunks. 2 documents -> into the vector storage. Also geussing source from the file extension
2026-02-11 11:23:50 +03:00
1e6ab247b9
Phase 12 done... loading via adaptive collection, yadisk or local
2026-02-10 22:19:27 +03:00
e9dd28ad55
Prep for Phase 12 of loading files for enrichment through the adaptive collections
2026-02-10 21:42:59 +03:00
06a3155b6b
Working Yandex Disk integration for loading files. Tests for local and Yandex
2026-02-10 20:42:07 +03:00
63c3e2c5c7
Adaptive Collection, and Phase 11 WIP
2026-02-10 20:12:43 +03:00
447ecaba39
enrichment with years, events
2026-02-10 13:20:19 +03:00
ce62fd50ed
Created this MD file to store things we need to look out to
2026-02-09 21:33:03 +03:00
2cb9b39bf2
removed test retrieval feature. off you go
2026-02-09 21:17:42 +03:00
f9c47c772f
llamaindex update + unpacking archives in data
2026-02-09 19:00:23 +03:00
0adbc29692
env step for llamaindex
2026-02-05 22:48:39 +03:00
effbc7d00f
proper usage of embedding models if defined in .env
2026-02-05 01:07:25 +03:00
31d198afb8
properly loading .env file with dotenv
2026-02-05 00:08:59 +03:00
833aad317a
quick fix to use openai instead of ollama, in vetor_storage.py
2026-02-05 00:04:10 +03:00
f87f3c0cdd
moved demo.html into demo-ui folder and renamed to index.html for ease of server serving... lol
2026-02-04 23:36:23 +03:00
a6320985dd
resolved conflicts in requirements.txt
2026-02-04 23:34:37 +03:00
69e7ecee62
Updated requirements.txt file
2026-02-04 23:13:27 +03:00
8c57921b7f
Working demo.html with connection to the api endpoint
2026-02-04 23:13:00 +03:00
9188b672c2
preparations for demo html page
2026-02-04 22:50:24 +03:00
bf3a3735cb
openai compatible integration done
2026-02-04 22:30:57 +03:00
ae8c00316e
Langchain plan phases for openai integration (openai compaible endpoint), server for retrieving data
2026-02-04 21:34:22 +03:00
ea4ce23cd9
Retrieval and also update on russian language
2026-02-04 16:51:50 +03:00
3dea3605ad
Enrichment for llamaindex. It goes for a long time using local model, so better use external model not local, for EMBEDDING
2026-02-04 16:06:01 +03:00
f36108d652
Vector storage Qdrant initialization and configuration
2026-02-04 01:10:07 +03:00
c37aec1d99
File extensions and libraries for llamaindex
2026-02-04 01:02:21 +03:00
fa26d77520
Cli with ping for llamaindex
2026-02-04 00:59:01 +03:00
86fd643e66
Start of work on Llamaindex framework
2026-02-04 00:49:45 +03:00
d354d3dcca
Working chat with AI agent with retrieving data
2026-02-04 00:02:53 +03:00
299ee0acb5
Working retrieval with the cli
2026-02-03 23:25:24 +03:00
4cbd5313d2
Working enrichment
2026-02-03 22:55:12 +03:00
8d7e39a603
langchain loading documents into vector storage
2026-02-03 20:52:08 +03:00
762ed89843
langchain vector storage connection and confguration
2026-02-03 20:42:09 +03:00
cd7c96e022
langchain extensions for data files and their libraries
2026-02-03 20:17:13 +03:00
d99433d087
langchain done cli
2026-02-03 19:51:35 +03:00
351fe27cca
Initial commit
2026-02-03 19:24:41 +03:00
