111 Commits

Author SHA1 Message Date
Adityavardhan Agrawal
8712bb49e0 Update readme, add more examples 2025-03-20 22:54:18 -04:00
Adityavardhan Agrawal
adc0b2dbb8
Add batch ingestion (#55) 2025-03-18 23:27:53 -04:00
LukeZekes
5d76521059
Change in max_sim function for newer postgresql versions (#54)
* add filename option for text documents

* fix: duplicated env variables

* Include chunk score in query response

* don't initialize colpali store if one is not provided

* Add score to ChunkSource

* Add huggingface cache volume to avoid redownloads

* Replace <~> in maximum_similarity calculation

* Add dev_mode setup to default configuration

* Dump with databridge documents (no pdfs)

* Add dev_mode setup to default configuration

* Comment docker instructions for api host

* Use empty dump file
2025-03-18 14:41:39 -04:00
Adityavardhan Agrawal
9df9196d51 Publish graphs on pypi, update version 2025-03-17 18:40:03 -04:00
Adityavardhan Agrawal
4ae132ff46
Implement knowledge graphs, and graph enhanced querying (#48) 2025-03-17 17:36:43 -04:00
Arnav Agrawal
989d25d8c7 colpali hotfix 2025-03-16 17:08:38 -04:00
Adityavardhan Agrawal
32a5d787fe
Add update methods with add update strategy (#53) 2025-03-13 11:26:01 -04:00
Adityavardhan Agrawal
dbbc7142a8
Update README.md 2025-03-13 00:48:11 -04:00
Adityavardhan Agrawal
ef2357b145
Update README.md 2025-03-13 00:44:02 -04:00
Arnav Agrawal
62342d1b57 make compatible with python3.11 2025-03-11 20:21:08 -04:00
LukeZekes
39d7bc7bfd
Include chunk score in query response and don't attempt to initialize colpali store if it is disabled (#52) 2025-03-11 15:53:42 -04:00
Adityavardhan Agrawal
38683df0f3
Add completion sources and batch retrieval for docs and chunks (#51) 2025-03-09 18:42:04 -04:00
Adityavardhan Agrawal
8c77da3708 Update readme 2025-03-05 12:40:13 -05:00
LukeZekes
e56691a1c5
add filename option for text documents (#47) 2025-03-05 10:56:02 -05:00
Arnav Agrawal
186c76a799
Update README.md 2025-03-04 21:30:43 -05:00
Arnav Agrawal
59f14946ae
improve ui-component (#46) 2025-03-03 18:05:51 -05:00
Arnav Agrawal
8428616dd6 add support for .docx files 2025-02-28 15:06:59 -05:00
Arnav Agrawal
871b07943a
add colpali and remove content_type from ingestion pathway (#45) 2025-02-28 14:37:46 -05:00
Arnav Agrawal
1cf6b16ddb
Update README.md 2025-02-28 13:26:54 -05:00
Arnav Agrawal
8fd545e1d6 add colpali example 2025-02-28 12:16:06 -05:00
Arnav Agrawal
07eec6b9e3 add image processing to ollama 2025-02-26 22:36:25 -05:00
Arnav Agrawal
821e9d7e20
Add support for ColPali (#43)
* debug mps not supported

* further debug (i think i lost some braincells)

* fix mps bug and resolve dependency issues

* remove libmagic dependence

* add colpali embedding model

* multi-vector store works - verified with testing

* add integration testing

* support text embedding in colpali

* complete colplai integration and testing

* formatting + some PR comments

* remove experimental files

* resolve PR comments
2025-02-26 20:17:12 -05:00
Adityavardhan Agrawal
c8ed46b12b
Separate parsing and chunking into different function for easy rules processing (#41) 2025-02-15 13:02:15 -05:00
Arnav Agrawal
64e3629107
Update README.md 2025-02-10 23:47:07 -05:00
Arnav Agrawal
0d5a5b7f8f
add star history to README.md 2025-02-10 14:45:00 -05:00
Arnav Agrawal
75c1059117 add aggregate code to .gitignore 2025-02-10 10:50:50 -05:00
Adityavardhan Agrawal
1d733a7f84 Fix config start server issue 2025-02-08 00:09:36 -05:00
Adityavardhan Agrawal
a46fa064c7
Add natural language rules based ingestion (#34) 2025-02-07 21:08:40 -05:00
Adityavardhan Agrawal
5d54fecf26 Update README.md 2025-02-07 20:17:26 -05:00
Arnav Agrawal
9cdf8a589b
Create CODE_OF_CONDUCT.md 2025-02-06 14:58:34 -05:00
Christian Bonafena
41eac3dd3b
Fix: DocumentResponse interface in UI component (#35) 2025-02-02 23:24:24 -05:00
Adityavardhan Agrawal
ddefb40e17 Allow metadata addition and filtering in the ui component 2025-01-30 20:37:45 -05:00
Adityavardhan Agrawal
20c3015038 Fix video parsing bugs, improve server logging 2025-01-30 16:03:46 -05:00
Arnav Agrawal
d124e6aa0d
Add support for cache-augmented-generation (#30) 2025-01-28 23:49:28 -05:00
Adityavardhan Agrawal
4f0cf62008 Fix storage path for local storage and add clear table utility script 2025-01-22 16:57:09 -05:00
Adityavardhan Agrawal
055a091ade Add pdf utils to docker and add additional ref to .env 2025-01-22 09:12:12 -05:00
Adityavardhan Agrawal
54ad2041ae update and publish databridge-client version on pypi 2025-01-11 11:33:58 -05:00
Adityavardhan Agrawal
f4c14fc71b
Streamline dev experience with optional auth and simplified config (#27) 2025-01-11 11:24:00 -05:00
Adityavardhan Agrawal
13947d41bd
Add databridge UI component (#26) 2025-01-11 05:52:00 -05:00
Adityavardhan Agrawal
a3ddc2baae Delete fly-deploy.yml github action 2025-01-09 05:20:50 -05:00
Adityavardhan Agrawal
0a933e5fd6
Add docker support (#24) 2025-01-09 05:17:25 -05:00
Arnav Agrawal
9660a81120 fix quick setup for pgvector 2025-01-08 22:25:20 +05:30
Arnav Agrawal
3825ddcc2c update version on pypi 2025-01-07 15:33:59 +05:30
Arnav Agrawal
bd4d8f8178 update uri gen to match new config 2025-01-07 12:43:01 +05:30
Arnav Agrawal
f72f6f0249
Config improvements (#17) 2025-01-07 01:42:10 -05:00
Arnav Agrawal
f5666155c1
Update README.md 2025-01-07 00:45:28 -05:00
Adityavardhan Agrawal
aca3437c90 update readme 2025-01-06 14:10:12 -05:00
Arnav Agrawal
2a4fd05096
add better formatting for uri gen (#16) 2025-01-06 04:20:34 -05:00
Arnav Agrawal
32c3d1e052
Delete databridge.toml 2025-01-04 08:16:07 -05:00
Arnav Agrawal
c3726504f7
add support for PostgreSQL and pgvector (#15)
Co-authored-by: Adityavardhan Agrawal <aa729@cornell.edu>
2025-01-04 08:14:52 -05:00