Commit graph

2228 commits

Author SHA1 Message Date
sabaimran
c652a7fd2d Move text_to_entries under the new content folder 2023-11-21 22:25:17 -08:00
sabaimran
1e2af083f0 Rename the data_sources module to content 2023-11-21 22:11:32 -08:00
sabaimran
4cb28aeffb Resolve merge conflicts with master 2023-11-21 22:07:41 -08:00
Debanjum Singh Solanky
4cdfe8fc4f Re-enable Khoj Obsidian plugin for Mobile, as Khoj cloud is available 2023-11-21 16:33:48 -08:00
Debanjum
5d9d50157e
Clean Logs, Improve Message Rendering and Make Khoj Trusted Host Configurable (#561)
- Append chat message to chat logs as TextNodes in web, desktop clients

- Simplify Code to Identify Files from Github, Notion on Web, Desktop Client
  - Use file source to find entries from github, notion on web, desktop client
  - Pass file source to clients via text search API response

- Make Django Logs Follow Khoj Log Format, Verbosity
  - Handle image search setup related warning
  - Format Django initializing outputs using Khoj logger format

- Use `KHOJ_HOST` env var to set allowed/trusted domains to host Khoj
2023-11-21 15:14:34 -08:00
sabaimran
458e794d00 Revert PYTHONPATH to what it was before 2023-11-21 14:40:57 -08:00
Debanjum Singh Solanky
9e736d4340 Use KHOJ_DOMAIN for CORS allow_origins list as well
- Default to app.khoj.dev
- Remove unnecesary any_path regex in allow_origins. It only cares
  about host, paths are not set in origin header
2023-11-21 14:02:04 -08:00
sabaimran
5469e81a87 Use full path for the static directory in FastAPI and reflect deeper nesting of the django app 2023-11-21 13:44:45 -08:00
sabaimran
d199c4c35f Resovle merge conflicts with matser 2023-11-21 13:35:56 -08:00
Debanjum Singh Solanky
76d041f633 Use KHOJ_HOST env var to set allowed/trusted domains to host Khoj
Allows hosting Khoj behind other, non "khoj.dev" domains
2023-11-21 13:11:45 -08:00
Debanjum Singh Solanky
90d463c12a Append chat message to chat logs as TextNodes in web, desktop clients 2023-11-21 13:10:50 -08:00
Debanjum Singh Solanky
befcbcdd5d Use file source to find entries from github, notion on web, desktop client
This is a more robust mechanism of identification than via file name
including github or notion domain names
2023-11-21 13:10:50 -08:00
Debanjum Singh Solanky
3f0de45ec6 Pass file source to clients via text search API response
Source of entry stored in DB is now passed to clients for processing
2023-11-21 13:10:50 -08:00
Debanjum Singh Solanky
4aec581306 Handle image search setup related warning
Ideally should rename model_directory to config_directory or some such
but the current image search code will need to be migrated soon. So
changing the variable name and creating a migration script for old
khoj.yml files using model-directory variable isn't worth it

Remove the explicity set of number of threads to use by pytorch. Use
the default used by it.
2023-11-21 13:10:50 -08:00
Debanjum Singh Solanky
b06628ee31 Format Django initializing outputs using Khoj logger format
- Collect STDOUT from the `migrate', `collectstatic' commands and
  output using the Khoj logger format and verbosity settings

- Only show Django `collectstatic' command output in verbose mode

- Fix showing the Initializing Khoj log line by moving it after logger
  level set
2023-11-21 13:10:50 -08:00
Debanjum Singh Solanky
6d9091bef5 Disable isort for now 2023-11-21 13:03:18 -08:00
sabaimran
341abf03ff Handle none for search_type and use equals comparator rather than in for determining Notion type 2023-11-21 12:55:09 -08:00
Debanjum Singh Solanky
19e042037a Run isort with black profile to avoid conflicts between the two 2023-11-21 12:52:07 -08:00
sabaimran
2bb989e9d8 Resolve merge conflicts and fix some import ordering 2023-11-21 12:30:43 -08:00
sabaimran
244b76ffed Add isort for automatic import sorting and skip main.py because it's a drama queen 👑 2023-11-21 12:20:41 -08:00
Debanjum
8a0d92e2d7
Fix Connectivity Check in Obsidian Client (#559) from dtkav/bugfix-local-connectivity-check
Check connection to Khoj server for self-hosted server. This check had regressed during the cloud rearchitecture
2023-11-21 12:05:16 -08:00
sabaimran
0e6f09b241
Merge pull request #562 from khoj-ai/fix/pypi-package-app-not-included
Fix PyPi package app reference issue
2023-11-21 11:54:46 -08:00
sabaimran
61f6b8c0d4 Ignore-check step failed due to unrecognized code. Try using capital letters for indicator 2023-11-21 11:33:43 -08:00
sabaimran
38144a7a69 pull_request path should be src/khoj rather than src/ 2023-11-21 11:33:07 -08:00
Debanjum
e5130fb3f3
Fix ranking search results on Obsidian (#560)
This bug was causing the search results on the Obsidian client to be shown in the reverse order of their actual relevance.

It reversed since entry scores returned by Khoj server are a distance metric since the move to Postgres. So lesser distance is better. Previously higher score was better.
2023-11-21 11:32:47 -08:00
sabaimran
333cb3445c Use colon rather than equals to indicate typing 2023-11-21 11:28:51 -08:00
Debanjum Singh Solanky
645fd96634 Search across all content types from Khoj Obsidian client
Previously it was only searching for PDF and Markdown files. This was
meant to show only content from current vault as results.

But it has not scaled well as other clients also allow syncing PDF and
markdown files now. So remove this content type filter for now.

A proper solution would limit by using file/dir filters on server or
client side.
2023-11-21 11:19:33 -08:00
sabaimran
a1460a5bf9 Set operations to typed empty list in migration file 2023-11-21 11:14:40 -08:00
sabaimran
8932fc0c36 Ignore w004 check to bypass pypi warnings for check-wheel-contents
- PyPi doesn't like to have files that start with numbers, however all of the generated django migration files start with numbers. To accommodate, skip this check.
- Refer to https://pypi.org/project/check-wheel-contents/ for documentation and recommendation
2023-11-21 11:12:50 -08:00
sabaimran
71e794c26f Remove the sys.append line in the main.py file, as it's not required 2023-11-21 10:57:21 -08:00
sabaimran
a474c31e02 Move the django app into the src/khoj folder for better organization and functionality
- Our pypi package currently does not work because the django app and associated database is not included. To remedy this issue, move the app into the src/khoj folder. This has the added benefit of improved organization of the codebase, as all server related code is now in a single folder
- Update associated file paths and system references
2023-11-21 10:56:04 -08:00
Debanjum Singh Solanky
c89bd49973 Fix ranking search results on Obsidian
It's reversed since score of entries is now a distance metric on
Khoj server. So lesser distance is better. Previously higher score was
better
2023-11-21 01:24:59 -08:00
Debanjum
6d8e889917
Improve Self Hosted Khoj Setup (#557)
- c07401cf Fix, Improve chat config via CLI on first run by using defaults
- d61b0dd5 Add Khoj Django app package to sys path to load Django module via pip install
- 4e98acbc Update minimum pydantic version to one with model_validate function
2023-11-20 17:25:53 -08:00
Daniel Grossmann-Kavanagh
f142999bce fix khoj local server usage 2023-11-20 17:07:30 -08:00
Debanjum Singh Solanky
c07401cf76 Fix, Improve chat config via CLI on first run by using defaults
- Fix setting prompt size for online chat
- generally improve chat config via cli by using default chat model,
  prompt size for online and offline chat
2023-11-20 17:01:20 -08:00
sabaimran
b142de15a8 Merge branch 'features/internet-enabled-search' of github.com:khoj-ai/khoj into features/reflective-suggested-questions 2023-11-20 15:56:09 -08:00
sabaimran
a9623ef85a Add requisite imports in order to instantiate offline model in adapters file 2023-11-20 15:27:42 -08:00
sabaimran
a8f13f334f Fix merging issues with base after popping the stash 2023-11-20 15:22:50 -08:00
sabaimran
8fa0b69c67 Resolve merge issue with adapters methods 2023-11-20 15:21:06 -08:00
sabaimran
fee99779bf Add subqueries for internet-connected search results and update client-side code accordingly
- Add a wrapper method to help make direct queries to the LLM and determine any intermediate responses needed for handling the request
2023-11-20 15:19:15 -08:00
Debanjum Singh Solanky
d61b0dd55c Add Khoj Django app package to sys path to load Django module via pip install 2023-11-20 14:55:00 -08:00
Debanjum Singh Solanky
4e98acbca7 Update minimum pydantic version to one with model_validate function 2023-11-20 14:52:37 -08:00
sabaimran
b8e6883a81 Merge branch 'master' of github.com:khoj-ai/khoj into features/internet-enabled-search 2023-11-19 16:20:08 -08:00
sabaimran
237195e20e Make all name-related fields nullable within the GoogleUser 2023-11-19 14:22:32 -08:00
sabaimran
4def8cce36
Merge pull request #541 from asim-shrestha/patch-1
Add test separators
2023-11-19 14:14:34 -08:00
Debanjum
71799add0b
Index Parent Headings of Org-Mode Entries to Improve Search Context (#548)
### Overview
The parent hierarchy of org-mode entries can store important context. 
This change updates OrgNode to track parent headings for each org entry and adds the parent outline for each entry to the index

### Details
- Test search uses ancestor headings as context for improved results
- Add ancestor headings of each org-mode entry to their compiled form
- Track ancestor headings for each org-mode entry in org-node parser

Resolves #85
2023-11-19 13:18:19 -08:00
sabaimran
e398a76779 Fix test word filter 2023-11-19 13:14:58 -08:00
sabaimran
33a9304428 Resolve merge conflicts 2023-11-19 12:57:55 -08:00
sabaimran
cfd76b8472 Add open graph links to configure Khoj Docs preview 2023-11-19 12:16:59 -08:00
sabaimran
ef5e9d66c1 Resolve merge conflicts in dependency imports 2023-11-19 11:42:20 -08:00