Debanjum Singh Solanky
6ded4c1d75
Merge branch 'master' into fix-1000-file-index-update-limit
2024-01-16 16:50:58 +05:30
Debanjum Singh Solanky
16175137e5
Decode URL encoded query string in chat API endpoint before processing
2024-01-16 13:09:28 +05:30
Debanjum Singh Solanky
9fe1c8ae13
Make references and online_results optional params to converse_offline
...
Fixes all the failing GPT4All tests because they were missing the
online_results argument
2024-01-16 13:09:28 +05:30
Debanjum Singh Solanky
d74f8e03d3
Pass max context length to fix using updated GPT4All.list_gpu method
...
It's signature was updated in GPT4All 2.1.0 pypi release.
Resolves #610
2024-01-16 12:23:45 +05:30
Debanjum Singh Solanky
1ae6669fbf
Correctly handle API response when no files to index
2024-01-16 11:57:40 +05:30
sabaimran
50575b749b
Add option to use HuggingFace's inference endpoint for generating embeddings ( #609 )
...
* Support using hosted Huggingface inference endpoint for embeddings generation
* Since the huggingface inference endpoint is model-specific, make the URL an optional property of the search model config
* Handle ECONNREFUSED error in desktop app
* Drive API key via the search model config model and use more generic names
2024-01-16 08:58:24 +05:30
Debanjum Singh Solanky
ba37b28fb5
Improve batched error handling. Catch can't connect to server error
...
Break out of batch processing when unable to connect to server or
when requests throttled by server
2024-01-14 01:04:44 +05:30
Debanjum Singh Solanky
af9ceb00a0
Show relevant error msg in desktop app, e.g when can't connect to server
2024-01-09 23:09:34 +05:30
Debanjum Singh Solanky
43423432ce
Pass indexed filenames in API response for client validation
2024-01-09 23:09:34 +05:30
Debanjum Singh Solanky
5f9ac5a630
Collect files to index in single dict to simplify index/update controller
...
Simplifies code while maintaining typing
2024-01-09 23:09:34 +05:30
Debanjum Singh Solanky
efe41aaaca
Push 1000 files at a time from the Desktop client for indexing
...
FastAPI API endpoints only support uploading 1000 files at a time.
So split all files to index into groups of 1000 for upload to
index/update API endpoint
2024-01-09 23:09:34 +05:30
Debanjum Singh Solanky
b6d5392c0c
Release Khoj version 1.2.1
2024-01-04 18:45:37 +05:30
Debanjum Singh Solanky
fca7a5ff32
Push 1000 files at a time from the Obsidian client for indexing
...
FastAPI API endpoints only support uploading 1000 files at a time.
So split all files to index into groups of 1000 for upload to
index/update API endpoint
2024-01-04 18:43:22 +05:30
Debanjum Singh Solanky
4a234c8db3
Use default offline/openai chat model to extract DB search queries
...
Make usage of the first offline/openai chat model as the default LLM
to use for background tasks more explicit
The idea is to use the default/first chat model for all background
activities, like user message to extract search queries to perform.
This is controlled by the server admin.
The chat model set by the user is used for user-facing functions like
generating chat responses
2024-01-03 14:04:49 +05:30
Debanjum Singh Solanky
e28adf2884
Also index pdf, markdown and plaintext files using khoj emacs client
...
Previously you could only index org-mode files and directories from
khoj.el
Mark the `khoj-org-directories', `khoj-org-files' variables for
deprecation, since `khoj-index-directories', `khoj-index-files'
replace them as more appropriate names for the more general case
Resolves #597
2024-01-03 11:46:17 +05:30
Debanjum Singh Solanky
5abaed9d08
Use user chosen OpenAI model to extract DB search questions from query
...
Previously Khoj was selecting the first OpenAI model configured on
server and not the OpenAI model configured by the user for themselves
2024-01-03 11:45:06 +05:30
Debanjum Singh Solanky
05536aab6b
Merge how users can share personal information in personality prompt
2024-01-03 11:40:14 +05:30
Liam Swayne
455f78b178
Replace var declarations with let declarations ( #576 )
...
* Replace var declaration with let declaration
2023-12-29 10:20:48 +05:30
sabaimran
79913d4c17
Add isort to the pre-commit configuration and apply it to the whole project ( #595 )
...
* Apply isort to the entire repository
* Fix missing import issues in text_to_entries
* Fix imports in migration files
2023-12-28 18:04:02 +05:30
sabaimran
442c913de3
Update telemetry state for search model only if one is found, fix alt text for language setting
2023-12-28 12:53:53 +05:30
sabaimran
d3ab3f1b70
Rename matrix_blog to web and move the language setting into the content section
2023-12-28 12:44:49 +05:30
sabaimran
00af6baeb6
Resolve merge conflicts with intro message in chat.html web view
2023-12-23 17:52:58 +05:30
sabaimran
afec4394f9
Merge pull request #592 from ayushjha119/Fixed-Health-Check-to-Khoj-api
...
Fixed health check to khoj api
2023-12-23 13:04:50 +05:30
sabaimran
c50eb8a691
Fix mypy/pre-commit issues
2023-12-23 11:44:37 +05:30
Debanjum Singh Solanky
21c55b4c0d
Release Khoj version 1.2.0
2023-12-22 21:43:47 +05:30
Debanjum Singh Solanky
6a8c1fe423
Sanitize rendering chat references in Web, Desktop and Obsidian clients
...
Use textContent instead of innerHTML to append references
Resolves #583
2023-12-22 18:11:49 +05:30
Debanjum
6879daccc6
Fix Chat Streaming on Obsidian, Docker Image Version and First-Run, Chat Error Messages in Clients ( #589 )
...
- Fix streaming chat response in Obsidian client
- Fix first-run, chat error message in obsidian, desktop and web clients
- Set Khoj app version to latest version in Docker images
- Tag Khoj Docker image built on release with the `latest` tag
This align docker image release cadence with client, server releases
2023-12-22 04:13:01 -08:00
Debanjum Singh Solanky
d101297995
Use markdown formatted chat message in chat modal
2023-12-22 17:01:31 +05:30
Debanjum Singh Solanky
350fd89c8d
Clear chat history html in Obsidian if getChatHistory works too
2023-12-22 17:01:31 +05:30
ayushjha119
e487ec5370
fixed app to api health Check
2023-12-21 17:51:30 +05:30
Debanjum Singh Solanky
70607cbbbb
Update FRE message to get any Khoj client to sync files with server
2023-12-21 15:23:47 +05:30
ayushjha119
b3d7d6a79d
used the Response class from fastapi.responses and set the input for status_code to 200
2023-12-21 14:26:40 +05:30
sabaimran
e1aaff2053
Add more details about functionality in Khoj's intro message
2023-12-21 10:09:30 +05:30
sabaimran
a1211f40d7
Fix type declaration for the cross_encoder_model state variable. Update name of the new update API
2023-12-21 09:15:13 +05:30
sabaimran
089e4bee12
FIx unit tests with new search model configurations
2023-12-20 21:50:44 +05:30
Debanjum Singh Solanky
447c1b90e7
Fix streaming chat response in Obsidian client
...
- Convert renderIncrementalMessage to an async method as
MarkdownRenderer is an async method
- Simplify code, remove unneeded JSON check
2023-12-20 14:51:19 +05:30
sabaimran
aa23da60a3
Add a notification banner to show temporary messages
2023-12-20 14:22:08 +05:30
Debanjum Singh Solanky
e04fe921eb
Fix first-run, chat error message in obsidian, desktop and web clients
...
- Disable chat input field if getChatHistory had error as Khoj may not
be setup correctly to chat
2023-12-20 14:03:07 +05:30
sabaimran
5ff9df9d4c
Add support per user for configuring the preferred search model from the config page
...
- Honor this setting across the relevant places where embeddings are used
- Convert the VectorField object to have None for dimensions in order to make the search model easily configurable
2023-12-20 13:25:43 +05:30
sabaimran
0f6e4ff683
Add a model that specifies the user's search model configuration
...
- Update all endpoints that generate embeddings to use the new model. Incl. generating text embeddings, creating embeddings for a search query
2023-12-20 09:22:26 +05:30
sabaimran
6dd2b05bf5
Rebase with master
2023-12-19 21:02:49 +05:30
sabaimran
e3557cd8b7
Update the personality prompt to make Khoj aware that users can share data via the desktop app
2023-12-19 16:42:45 +05:30
sabaimran
927e477f68
Ignore typing error in custom action short description
2023-12-19 16:10:58 +05:30
sabaimran
946305d977
Add function to export conversations for debugging
2023-12-19 16:05:20 +05:30
sabaimran
903a01745f
Use 0px for padding for input row buttons in web
2023-12-18 16:09:06 +05:30
sabaimran
5b092d59f4
Ignore dict assignment typing error
2023-12-17 22:34:54 +05:30
sabaimran
03cb86ee46
Update typing and object assignment for new text to image method return
2023-12-17 21:28:33 +05:30
sabaimran
0288804f2e
Render the inferred query along with the image that Khoj returns
2023-12-17 21:02:55 +05:30
sabaimran
49af2148fe
Miscellaneous improvements to image generation
...
- Improve the prompt before sending it for image generation
- Update the help message to include online, image functionality
- Improve styling for the voice, trash buttons
2023-12-17 20:25:35 +05:30
sabaimran
7cb64cb2f9
Add telemetry for image generation conversation command
2023-12-17 18:25:03 +05:30
