Commit Graph

43 Commits

Author SHA1 Message Date
Sean Hatfield
288ff0d18c
fix vector cache not deleting cache after unembedding items with folders (#630) 2024-01-22 13:03:05 -08:00
Timothy Carambat
0db6c3b2aa
Prevent private octets from link collection for self-hosted (#626) 2024-01-19 10:49:40 -08:00
Timothy Carambat
b35feede87
570 document api return object (#608)
* Add support for fetching single document in documents folder

* Add document object to upload + support link scraping via API

* hotfixes for documentation

* update api docs
2024-01-16 16:04:22 -08:00
Timothy Carambat
1563a1b20f
Strict link protocol validation (#577) 2024-01-11 12:29:00 -08:00
Timothy Carambat
58971e8b30
Build & Publish AnythingLLM for ARM64 and x86 (#549)
* Update build process to support multi-platform builds
Bump @lancedb/vectordb to 0.1.19 for ARM&AMD compatibility
Patch puppeteer on ARM builds because of broken chromium
resolves #539
resolves #548

---------

Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
2024-01-08 16:15:01 -08:00
Francisco Bischoff
990a2e85bf
devcontainer v1 (#297)
Implement support for GitHub codespaces and VSCode devcontainers
---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
Co-authored-by: Sean Hatfield <seanhatfield5@gmail.com>
2024-01-08 15:31:06 -08:00
timothycarambat
26549df6a9 touchup linting 2023-12-27 13:28:37 -08:00
timothycarambat
daadad3859 hoist var in extensions 2023-12-20 19:41:16 -08:00
Timothy Carambat
f2fadd6d2e
Add placeholder collector ENV file (#476)
resolves #474
2023-12-19 13:27:09 -08:00
Timothy Carambat
ecf4295537
Add ability to grab youtube transcripts via doc processor (#470)
* Add ability to grab youtube transcripts via doc processor

* dynamic imports
swap out Github for Youtube in placeholder text
2023-12-18 17:17:26 -08:00
Timothy Carambat
452582489e
GitHub loader extension + extension support v1 (#469)
* feat: implement github repo loading
fix: purge of folders
fix: rendering of sub-files

* noshow delete on custom-documents

* Add API key support because of rate limits

* WIP for frontend of data connectors

* wip

* Add frontend form for GitHub repo data connector

* remove console.logs
block custom-documents from being deleted

* remove _meta unused arg

* Add support for ignore pathing in request
Ignore path input via tagging

* Update hint
2023-12-18 15:48:02 -08:00
timothycarambat
d2e3506bb9 fix: transition on LLM and embedding screen
linting
2023-12-15 12:40:11 -08:00
Timothy Carambat
61db981017
feat: Embed on-instance Whisper model for audio/mp4 transcribing (#449)
* feat: Embed on-instance Whisper model for audio/mp4 transcribing
resolves #329

* additional logging

* add placeholder for tmp folder in collector storage
Add cleanup of hotdir and tmp on collector boot to prevent hanging files
split loading of model and file conversion into concurrency

* update README

* update model size

* update supported filetypes
2023-12-15 11:20:13 -08:00
Timothy Carambat
719521c307
Document Processor v2 (#442)
* wip: init refactor of document processor to JS

* add NodeJs PDF support

* wip: partity with python processor
feat: add pptx support

* fix: forgot files

* Remove python scripts totally

* wip:update docker to boot new collector

* add package.json support

* update dockerfile for new build

* update gitignore and linting

* add more protections on file lookup

* update package.json

* test build

* update docker commands to use cap-add=SYS_ADMIN so web scraper can run
update all scripts to reflect this
remove docker build for branch
2023-12-14 15:14:56 -08:00
Timothy Carambat
da0cec7aa2
patch: remove unidecode as it was transliterating non-latin chars (#434)
resolves #298
2023-12-13 11:54:55 -08:00
Timothy Carambat
ce9233c258
feat: enable HTML uploads from UI (#422)
resolves #418
2023-12-11 14:40:33 -08:00
timothycarambat
b583aa74fd remove prints 2023-11-16 17:17:52 -08:00
Sean Hatfield
7edfccaf9a
Adding url uploads to document picker (#375)
* WIP adding url uploads to document picker

* fix manual script for uploading url to custom-documents

* fix metadata for url scraping

* wip url parsing

* update how async link scraping works

* docker-compose defaults added
no autocomplete on URLs

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2023-11-16 17:15:01 -08:00
Sean Hatfield
f40309cfdb
Add id to all metadata to prevent errors in frontend document picker (#378)
add id to all metadata to prevent errors in frontend docuemnt picker

Co-authored-by: timothycarambat <rambat1010@gmail.com>
2023-11-16 14:36:26 -08:00
timothycarambat
1e3d82e184 patch collector script 2023-11-16 10:25:23 -08:00
timothycarambat
c5dc68633b patch link scrape tool schema 2023-11-14 16:41:39 -08:00
Timothy Carambat
5441717294
normalize parser struct for all file types (#321) 2023-11-01 16:44:02 -07:00
Francisco Bischoff
26dba59249
mbox parsing improvements v1 (#308)
* mbox parsing improvements v1

* autobots roll out!
2023-10-30 11:57:33 -07:00
Timothy Carambat
18798c5b64
prevent deletion of documents not in hotdir via director traversal (#258)
resolves #257
2023-09-29 11:04:47 -07:00
Timothy Carambat
a505928934
Display better error messages from document processor (#243)
pass messages to frontend on success/failure
resolves #242
2023-09-18 16:50:20 -07:00
Timothy Carambat
3e78476739
Franzbischoff document improvements (#241)
* cosmetic changes to be compatible to hadolint

* common configuration for most editors until better plugins comes up

* Changes on PDF metadata, using PyMuPDF (faster and more compatible)

* small changes on other file ingestions in order to try to keep the fields equal

* Lint, review, and review

* fixed unknown chars

* Use PyMuPDF for pdf loading for 200% speed increase
linting

---------

Co-authored-by: Francisco Bischoff <franzbischoff@gmail.com>
Co-authored-by: Francisco Bischoff <984592+franzbischoff@users.noreply.github.com>
2023-09-18 16:21:37 -07:00
Melroy van den Berg
16b8330fbf
Update requirements.txt (#185)
Upgrade fake-useragent to latest version (v1.2.1). Disclaimer: I'm the package maintainer.
2023-08-14 14:38:14 -07:00
Timothy Carambat
b42493c6de
Split large PDFS into subfolder in documents (#176)
append time value to folder name to prevent duplicate uploads
2023-08-03 18:57:50 -07:00
AntonioCiolino
31e5db7490
Twitter Feature (#134)
* .

* twitter feature update

* Key validation and operation
2023-07-06 14:05:50 -07:00
Timothy Carambat
d7315b0e53
be able to parse relative and FQDN links from root reliabily (#138) 2023-07-05 14:40:54 -07:00
mplawner
3efe55a720
Added mbox support (#106)
* Update filetypes.py

Added mbox format

* Created new file

Added support for mbox files as used by many email services, including Google Takeout's Gmail archive.

* Update filetypes.py

* Update as_mbox.py
2023-06-25 18:11:05 -07:00
AntonioCiolino
a52b0ae655
Updated Link scraper to avoid NoneType error. (#90)
* Enable web scraping based on a urtl and a simple filter.

* ignore yarn

* Updated Link scraper to avoid NoneType error.
2023-06-19 12:07:26 -07:00
frasergr
4079020de0
dockerfile cleanup; enforce text LF line endings (#81) 2023-06-17 20:18:01 -07:00
AntonioCiolino
e7ba028497
Enable web scraping based on a urtl and a simple filter. (#73) 2023-06-16 17:29:11 -07:00
timothycarambat
81b2159329 reorder docs 2023-06-16 17:26:42 -07:00
Timothy Carambat
c4eb46ca19
Upload and process documents via UI + document processor in docker image (#65)
* implement dnd uploader
show file upload progress
write files to hotdirector
build simple flaskAPI to process files one off

* move document processor calls to util
build out dockerfile to run both procs at the same time
update UI to check for document processor before upload
* disable pragma update on boot
* dockerfile changes

* add filetype restrictions based on python app support response and show rejected files in the UI

* cleanup

* stub migrations on boot to prevent exit condition

* update CF template for AWS deploy
2023-06-16 16:01:27 -07:00
AntonioCiolino
537a6a91d2
Update __HOTDIR__.md (#70)
fixed typo for text.
2023-06-16 11:17:18 -07:00
Skid Vis
4118c9dcf3
Blocks images in sitemaps from being parsed. (#56)
* Adds ability to import sitemaps to include a website

* adds example sitemap url

* adds filter to bypass common image formats

* moves filetype ignoring to sitemap script
2023-06-14 23:00:03 -07:00
Skid Vis
bd32f97a21
Adds ability to import sitemaps to include a website (#51)
* Adds ability to import sitemaps to include a website

* adds example sitemap url
2023-06-14 11:04:17 -07:00
frasergr
9f33b3dfcb
Docker support (#34)
* Updates for Linux for frontend/server

* frontend/server docker

* updated Dockerfile for deps related to node vectordb

* updates for collector in docker

* docker deps for ODT processing

* ignore another collector dir

* storage mount improvements; run as UID

* fix pypandoc version typo

* permissions fixes
2023-06-13 11:26:11 -07:00
Fabio
d954d7a3d5
Fix pypandoc issue in requirements.txt (#23)
Co-authored-by: Carvalho, Fabio <Fabio_Carvalho@comcast.com>
2023-06-12 11:21:11 -07:00
timothycarambat
728eaff773 fix typo 2023-06-09 11:23:53 -07:00
timothycarambat
27c58541bd inital commit 2023-06-03 19:28:07 -07:00