f7382b0d2b
feat: returning events and locations from end point
2025-03-20 18:34:11 +00:00
47dd025ae3
feat: working e2e solution
2025-03-20 17:59:00 +00:00
f114ca06d8
merging
2025-03-19 09:46:52 +00:00
20213ff17b
feat: adding events and locations to json schema
2025-03-19 09:46:42 +00:00
9932568986
feat(events): also working
2025-03-18 18:37:12 +00:00
3a0f93e406
feat(locations): now working
2025-03-18 18:18:01 +00:00
b09063f74a
refactor(text,tags,links): to foreign key to image instead of user_image
2025-03-18 17:48:38 +00:00
a3e1db3d77
Merge branch 'main' of https://git.johncosta.tech/JohnCosta27/Haystack
2025-03-17 21:01:15 +01:00
5a766b8371
wip
2025-03-17 21:00:52 +01:00
4b120982d0
fix: returning whole tag object
2025-03-16 18:29:15 +00:00
7582e4d8d9
fix: returns correct image ID
2025-03-16 18:20:29 +00:00
8acf25a2a7
refactor(models): using more organised structure
2025-03-16 18:13:30 +00:00
536a49fe1c
feat(tags): correctly inserting new tags and adding them to images
2025-03-11 22:47:28 +00:00
40e854fb87
feat(tags): creating and getting user tags
2025-03-11 21:23:41 +00:00
5df6c67ee5
feat: new schema to support user tags better
2025-03-11 20:29:56 +00:00
863716c096
feat: super basic image search
2025-03-08 15:37:10 +00:00
53ebbb6e8d
feat: sending images and receiving them is now working
2025-03-08 13:13:05 +00:00
bf07c18fd7
feat: sending base64 image to backend
...
This is silly, but binary is apparently hard to do????
2025-03-08 12:30:16 +00:00
1424ec22f4
fix: using json response header
2025-03-07 14:14:40 +00:00
e595783d89
wip: Using mistral instead of OpenAi
2025-03-07 13:42:50 +00:00
7e7f3ff732
feat: making prompt be more generic with tags
2025-02-26 20:53:12 +00:00
3fe48464e4
feat: using different prompt
2025-02-26 20:49:55 +00:00
d1d6ee6762
fix: some spam from get images request
2025-02-26 20:48:52 +00:00
ad61b8e1fa
fix: getting user images
2025-02-26 20:09:19 +00:00
d8095b0c67
refactor: tables for image and processing_image
...
This allows a single table to be used to process images, meaning if
anything happens to the system we can always return to polling the
database and process these images individually.
Because of this we also want an `image` table to contain the actual
binary data for the image, so we aren't selecting and writing it each
time, as it is potentially a bottleneck.
2025-02-26 20:01:56 +00:00
410270e217
refactor: using chi router + bug fixes
2025-02-26 18:04:30 +00:00
5bec6c9590
fix: actually saving to the correct db table
2025-02-26 15:54:27 +00:00
971f705288
fix: actually returning all the user images
...
fix
2025-02-24 21:19:59 +00:00
13ebd80ce9
chore: documentation
2025-02-24 21:04:25 +00:00
b99432c202
feat: saving AI information to database
2025-02-24 21:00:05 +00:00
ee0587a16b
feat: method for getting images
2025-02-24 20:05:56 +00:00
64f6bde6a9
feat: methods to get image
2025-02-24 20:02:58 +00:00
f49589907a
feat: instructions for docker compose
2025-02-24 20:02:54 +00:00
2115da85b5
feat: working docker image and compose file
2025-02-24 19:44:19 +00:00
43092fa4f5
feat: using parsing on response
2025-02-24 19:05:11 +00:00
46e4043994
chore: updating gitignore
...
fix
2025-02-24 19:01:18 +00:00
24ef31e00f
feat: parsing response from open ai
...
bruh
2025-02-24 19:01:18 +00:00
97b1619b01
refactor: moving all files to backend
2025-02-22 23:30:59 +00:00
