591 Commits

Author SHA1 Message Date
Yuhong Sun
65d38ac8c3
Slack to respect LLM chunk filter settings (#768) 2023-11-26 01:06:12 -08:00
Yuhong Sun
8391d89bea
Fix Indexing Concurrency (#767) 2023-11-25 21:40:36 -08:00
Yuhong Sun
ac2ed31726
Indexing Jobs to have shorter lived DB sessions (#766) 2023-11-24 21:38:16 -08:00
Chris Weaver
47f947b045
Use torch.multiprocessing + enable SimpleJobClient by default (#765) 2023-11-24 18:29:28 -08:00
Weves
3cec854c5c Allow different model servers for different models / indexing jobs 2023-11-23 23:39:03 -08:00
Weves
26c6651a03 Improve LLM answer parsing 2023-11-23 15:03:35 -08:00
Yuhong Sun
13001ede98
Search Regression Test and Save/Load State updates (#761) 2023-11-23 00:00:30 -08:00
Yuhong Sun
fda377a2fa
Regression Script for Search quality (#760) 2023-11-22 19:33:28 -08:00
Yuhong Sun
bdfb894507
Slack Role Override (#755) 2023-11-22 17:47:18 -08:00
Weves
35c3511daa Increase Vespa timeout 2023-11-22 01:42:59 -08:00
Chris Weaver
c1e19d0d93
Add selected docs in UI + rework the backend flow a bit(#754)
Changes the flow so that the selected docs are sent over in a separate packet rather than as part of the initial packet for the streaming QA endpoint.
2023-11-21 19:46:12 -08:00
mattboret
e78aefb408
Add script to analyse the sources selection (#721)
---------

Co-authored-by: Matthieu Boret <matthieu.boret@fr.clara.net>
2023-11-21 18:35:26 -08:00
Bryan Peterson
aa2e859b46
add missing dependencies in model_server dockerfile (#752)
Thanks for catching this! Super helpful!
2023-11-21 17:59:28 -08:00
Yuhong Sun
c0c8ae6c08
Minor Tuning for Filters (#753) 2023-11-21 15:47:58 -08:00
Weves
1225c663eb Add new env variable to compose file 2023-11-20 21:40:54 -08:00
Weves
e052d607d5 Add option to log Vespa timing info 2023-11-20 21:37:22 -08:00
Yuhong Sun
8e5e11a554
Add md files to File Connector (#749) 2023-11-20 19:56:06 -08:00
Yuhong Sun
57f0323f52
NLP Model Warmup Reworked (#748) 2023-11-20 17:28:23 -08:00
Weves
6e9f31d1e9 Fix ResourceLogger blocking main thread 2023-11-20 16:46:18 -08:00
Weves
eeb844e35e Fix bug with Google Drive shortcut error case 2023-11-20 16:34:07 -08:00
Sid Ravinutala
d6a84ab413 fix for url parsing google site 2023-11-20 16:08:43 -08:00
Yuhong Sun
0cc3d65839
Add option to run a faster/cheaper LLM for secondary flows (#742) 2023-11-19 17:48:42 -08:00
Weves
df37387146 Fix a couple bugs with google sites link finding 2023-11-19 15:35:54 -08:00
Yuhong Sun
f72825cd46
Provide Metadata to the LLM (#740) 2023-11-19 12:28:45 -08:00
Yuhong Sun
6fb07d20cc
Multilingual Query Expansion (#737) 2023-11-19 10:55:55 -08:00
Chris Weaver
b258ec1bed
Adjust checks for removal from existing_jobs dict + add more logging + only one scheduled job for a connector at a time (#739) 2023-11-19 02:03:17 -08:00
Yuhong Sun
4fd55b8928
Fix GPT4All (#738) 2023-11-18 21:21:02 -08:00
Yuhong Sun
fa0d19cc8c
LLM Chunk Filtering (#735) 2023-11-18 17:12:24 -08:00
Weves
d5916e420c Fix duplicated query event for 'answer_qa_query_stream' and missing llm_answer in 'answer_qa_query' 2023-11-17 21:10:23 -08:00
Weves
ae72cd56f8 Add a bit more logging in indexing pipeline 2023-11-16 12:00:19 -08:00
Yuhong Sun
be5ef77896
Optional Anonymous Telemetry (#727) 2023-11-16 09:22:36 -08:00
Weves
0ed8f14015 Improve Vespa filtering performance 2023-11-15 14:30:12 -08:00
Weves
a03e443541 Add root_page_id option for Notion connector 2023-11-15 12:46:41 -08:00
Weves
81cbcbb403 Fix connector deletion bug 2023-11-14 09:07:59 -08:00
Yuhong Sun
69644b266e
Hybrid Search Alpha Parameter (#714) 2023-11-09 17:11:10 -08:00
Yuhong Sun
5a4820c55f
Skip Index on Docs with no newer updated at (#713) 2023-11-09 16:27:32 -08:00
Weves
a5d69bb392 Add back end time to Gong 2023-11-09 14:03:46 -08:00
Weves
23ee45c033 Enhance document explorer 2023-11-09 00:58:51 -08:00
Yuhong Sun
31bfd015ae
Request Tracker Connector (#709)
Contributed by Evan! Thanks for the contribution!

- Minor linting and rebasing done by Yuhong, everything else from Evan

---------

Co-authored-by: Evan Sarmiento <e.sarmiento@soax.com>
Co-authored-by: Evan <esarmien@fas.harvard.edu>
2023-11-07 16:55:10 -08:00
Yuhong Sun
0125d8a0f6
Source Filter Extraction (#708) 2023-11-07 14:21:04 -08:00
Yuhong Sun
4f64444f0f
Fix Version from Tag not picked up (#705) 2023-11-06 20:01:20 -08:00
Weves
abf9cc3248 Add timeout to all Notion calls 2023-11-06 19:29:42 -08:00
Chris Weaver
f5bf2e6374
Fix experimental checkpointing + move check for disabled connector to the start of the batch (#703) 2023-11-06 17:14:31 -08:00
Yuhong Sun
7433dddac3
Model Server (#695)
Provides the ability to pull out the NLP models into a separate model server which can then be hosted on a GPU instance if desired.
2023-11-06 16:36:09 -08:00
Weves
fe938b6fc6 Add experimental checkpointing 2023-11-04 14:51:28 -07:00
dependabot[bot]
2db029672b
Bump pypdf from 3.16.4 to 3.17.0 in /backend/requirements (#667)
Bumps [pypdf](https://github.com/py-pdf/pypdf) from 3.16.4 to 3.17.0.
- [Release notes](https://github.com/py-pdf/pypdf/releases)
- [Changelog](https://github.com/py-pdf/pypdf/blob/main/CHANGELOG.md)
- [Commits](https://github.com/py-pdf/pypdf/compare/3.16.4...3.17.0)

---
updated-dependencies:
- dependency-name: pypdf
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2023-11-03 18:54:29 -07:00
Yuhong Sun
602f9c4a0a
Default Version to 0.2-dev (#690) 2023-11-03 18:37:01 -07:00
Bradley
551705ad62
Implemented Danswer versioning system. (#649)
* Web & API server versioning system. Displayed on UI.

* Remove some debugging code.

* Integrated backend version into GitHub Action & Docker build workflow using env variables.

* Fixed web container environment variable name.

* Revise Dockerfiles for GitHub Actions workflow.

* Added system information page to admin panel with version info. Updated github workflows to include tagged version, and corresponding changes in the dockerfiles and codebases for web&backend to use env variables if present. Changed to 'dev' naming scheme if no env var is present to indicate local setup. Removed version from admin panel header.

* Added missing systeminfo dir to remote repo.
2023-11-03 18:02:39 -07:00
Weves
d9581ce0ae Fix Notion recursive search for non-shared database 2023-11-03 15:46:23 -07:00
Yuhong Sun
e27800d501 Formatting 2023-11-02 23:31:19 -07:00