Commit Graph

318 Commits

Author SHA1 Message Date
Kris 18ecc843e5
UX: move templates to main LLM config tab, restyle (#813)
Restructures LLM config page so it is far clearer. 

Also corrects bugs around adding LLMs and having LLMs not editable post addition 
---------

Co-authored-by: Sam Saffron <sam.saffron@gmail.com>
2024-09-30 17:15:11 +10:00
chapoi 8cf1798afe
UX: AI composer helper z-index issue (#809) 2024-09-23 17:01:04 -04:00
Keegan George 95f80325e5
DEV: Prevent close of summary from outside clicks (#808)
Often it is helpful to have the summary box open while composing a reply to the topic. However, the summary box currently gets closed each time you click outside the box. In this PR we add `closeOnClickOutside: false` attribute to the `DMenu` options for summary box to prevent that from occurring.
2024-09-18 10:36:42 -07:00
Keegan George e666266473
DEV: Make indicator wave a reusable component (#807)
Previously we had some hardcoded markup with scss making a loading indicator wave. This code was being duplicated and used in both semantic search and summarization. We want to add the indicator wave to the AI helper diff modal as well and have the text flashing instead of the loading spinner. To ensure we do not repeat ourselves, in this PR we turn the summary indicator wave into a reusable template only component called: `AiIndicatorWave`. We then apply the usage of that component to semantic search, summarization, and the composer helper modal.
2024-09-18 09:53:54 -07:00
chapoi 1e155942bb
UX: take composer height into account when calculating the max-height for topic summary (#806)
* remove unused import

* UX: take composer height into account when calculating the max-height for the topic summary
2024-09-18 14:54:41 +10:00
Keegan George 513510d6d0
FIX: AI Helper not visible on iPads (#805)
This commit fixes an issue where the composer AI helper was not visible on iPad in DiscourseHub. This was due to the z-index being different for `reply-control` when Discourse Hub inserts its `footer-nav`
2024-09-17 16:43:15 -07:00
Keegan George 493d65af1f
FIX: Diff modal closing along with composer menu on mobile (#803)
The `DiffModal` is triggered after selecting an option in the composer helper menu. After selecting an option, we should close the composer helper menu and only show the diff modal. On mobile, there was an edge-case where `this.args.close()` for was causing the closing of both the `DiffModal` and the `AiComposerHelperMenu`. This PR resolves that by ensuring the menu is closed _first_ asynchronously, followed by opening the relevant modal.
2024-09-16 14:00:41 -07:00
Keegan George b16390ae2a
UX: Improve toast message location (#800) 2024-09-14 09:19:13 +10:00
Keegan George 9374cd7ac1
FIX: Keyboard shortcut should be platform specific (#801) 2024-09-14 09:18:07 +10:00
Keegan George 9cd14b0003
DEV: Move composer AI helper to toolbar (#796)
Previously we had moved the AI helper from the options menu to a selection menu that appears when selecting text in the composer. This had the benefit of making the AI helper a more discoverable feature. Now that some time has passed and the AI helper is more recognized, we will be moving it back to the composer toolbar.

This is better because:
- It consistent with other behavior and ways of accessing tools in the composer
- It has an improved mobile experience
- It reduces unnecessary code and keeps things easier to migrate when we have composer V2.
- It allows for easily triggering AI helper for all content by clicking the button instead of having to select everything.
2024-09-13 11:59:30 -07:00
chapoi 22d1e71dc9
UX: AI post helper DMenu styling (#770) 2024-09-11 05:45:48 +02:00
Roman Rizzi c4c9dc2034
FIX: Display cached summaries with our new streamer. (#792)
Make sure the summary box is in the DOM before attempting to
display a cached summary.:
2024-09-03 18:45:28 -03:00
Kris 4a1874265e
UX: replace "share" with "share-alt" icon (#784) 2024-08-30 12:13:09 -03:00
Keegan George 4176fbd3dd
UX: Summary container should be fixed instead of growing (#783) 2024-08-29 16:32:05 -07:00
Keegan George fdadfa029e
FEATURE: smooth streaming animation for summarization (#778) 2024-08-29 15:07:07 -07:00
Sam 41054c4fb8
FEATURE: improve site setting search (#780)
This improves the site setting search so it performs a somewhat
fuzzy match.

Previously it did not handle seperators such as "space" and a
term such as "min_post_length" would not find "min_first_post_length"

A more liberal search algorithm makes it easier to the AI to
navigate settings.

* Minor fix, {{and parameter.enum parameter.enum.length}} is non
obviously broken.


If parameter.enum is a tracked array it will return the object
cause embers and helper implementation.

This corrects an issue where enum keeps on selecting itself by
mistake.
2024-08-29 16:05:38 +10:00
Keegan George 943504049c
FIX: Prevent proofreading when there is no content (#779) 2024-08-28 12:21:34 -07:00
Rafael dos Santos Silva a08d168740
FEATURE: Initial support for seeded LLMs (#756) 2024-08-28 15:57:58 -03:00
Jarek Radosz 1b209f5fb1
DEV: Update ace-editor usage (#773)
AceEditor is now a glimmer component (see: https://github.com/discourse/discourse/pull/28492) and it follows the "data down, actions up" pattern.
2024-08-27 13:52:55 +02:00
Keegan George 50c2d56aff
UX: Topic summary UI improvements due to DMenu changes (#772)
Co-authored-by: chapoi <101828855+chapoi@users.noreply.github.com>
2024-08-26 08:32:39 -07:00
Sam f148452f4c
FEATURE: single click proofreading (#769)
Previously there was too much work proofreading text, new implementation
provides a single shortcut and easy way of proofreading text.


Co-authored-by: Martin Brennan <martin@discourse.org>
2024-08-26 15:43:40 +10:00
Roman Rizzi 9019e90b87
FIX: urlEditable must be true for all providers except Bedrock (#766) 2024-08-22 11:31:28 -03:00
David Taylor 3c7bd9bbd3
FIX: Tool editing code editor resetting on every keypress (#765)
`withEventValue` is not needed here, because the `onChange` event comes from ace, not a normal DOM event. But even with that fix, it seems AceEditor doesn't yet work well with the DDAU pattern. On every keypress, the editor re-renders and puts the cursor back at the beginning.

For now, this commit removes the `@onChange` hook, so we go back to relying on the two-way binding of `@content`.

Followup to a5a39dd2ee
2024-08-22 10:18:16 +01:00
chapoi 324af23b72
UX: add dark-light mixin for better visibility in dark themes (#764) 2024-08-22 01:24:18 +02:00
Keegan George da9e192949
FIX: Mobile composer helper trigger should work on Android and iOS (#763) 2024-08-21 16:19:25 -07:00
chapoi 10dae65740
UX: style & position AI helper in composer (#758)
Co-authored-by: Keegan George <kgeorge13@gmail.com>
2024-08-21 11:01:03 -07:00
Roman Rizzi 64641b6175
FEATURE: LLM Triage support for systemless models. (#757)
* FEATURE: LLM Triage support for systemless models.

This change adds support for OSS models without support for system messages. LlmTriage's system message field is no longer mandatory. We now send the post contents in a separate user message.

* Models using Ollama can also disable system prompts
2024-08-21 11:41:55 -03:00
Keegan George c0328267be
FIX: Add original upload markdown on caption failure (#762) 2024-08-20 12:53:51 -07:00
Keegan George 4a40531143
FIX: Clicking on summary links breaks summary (#759) 2024-08-20 10:57:23 -03:00
Keegan George bfe3b1c3b8
FIX: Modals in composer helper menu not working (#755) 2024-08-16 10:08:58 -07:00
Keegan George 867cd54556
DEV: Reduce megapixel requirement for auto image captioning (#754) 2024-08-14 11:26:56 -07:00
Keegan George 23b88537d9
FIX: Prevent AI caption setting from showing unless all criteria is met (#753) 2024-08-14 10:17:36 -07:00
Sam 14443bf890
FIX: more robust summary implementation (#750)
When navigating between topic we were not correctly resetting
internal state for summarization. This leads to a situation where
incorrect summaries can be displayed to users and wrong summaries
can be displayed.

Additionally our controller for grabbing summaries was always
streaming results via message bus, which could be delayed when
sidekiq is overloaded. We now will return the cached summary
right away if it is available direct from REST endpoint.
2024-08-13 08:47:47 -03:00
Keegan George f72ab12761
DEV: Clearly separate post/composer helper settings (#747) 2024-08-12 15:40:23 -07:00
Keegan George a1eb1ba180
FIX: AI helper not being shown on mobile view (#749) 2024-08-12 15:32:49 -07:00
Keegan George 1d6a6c9f8f
FEATURE: Stream other post helper options (#745) 2024-08-08 11:32:39 -07:00
Roman Rizzi 20efc9285e
FIX: Correctly save provider-specific params for new models. (#744)
Creating a new model, either manually or from presets, doesn't initialize the `provider_params` object, meaning their custom params won't persist.

Additionally, this change adds some validations for Bedrock params, which are mandatory, and a clear message when a completion fails because we cannot build the URL.
2024-08-07 16:08:56 -03:00
Keegan George 1254d7c7d0
REFACTOR: AI Composer Helper Menu (#715) 2024-08-06 10:57:39 -07:00
Roman Rizzi 7b4c099673
FIX: LlmModel validations. (#742)
- Validate fields to reduce the chance of breaking features by a misconfigured model.
- Fixed a bug where the URL might get deleted during an update.
- Display a warning when a model is currently in use.
2024-08-06 14:35:35 -03:00
chapoi d17bbc2dc4
UX: summary fixed positioning (#740)
Co-authored-by: Rafael Silva <xfalcox@gmail.com>
2024-08-05 12:39:08 -03:00
Keegan George 2ff3fe3a9f
UX: Use stacked line chart for post sentiment (#737) 2024-08-02 14:23:29 -07:00
Rafael dos Santos Silva 9d887ad4ac
FIX: Use correct date for cached summary (#733) 2024-07-31 15:21:26 -03:00
Roman Rizzi bed044448c
DEV: Remove old code now that features rely on LlmModels. (#729)
* DEV: Remove old code now that features rely on LlmModels.

* Hide old settings and migrate persona llm overrides

* Remove shadowing special URL + seeding code. Use srv:// prefix instead.
2024-07-30 13:44:57 -03:00
Jan Cernik d58913b227
FIX: Collapse `Summarize` button on mobile (#726) 2024-07-25 16:10:53 -03:00
Jan Cernik d9dad56c6a
UX: Use `DMenu` for topic summarization (#724) 2024-07-25 10:47:18 -03:00
Roman Rizzi 5c196bca89
FEATURE: Track if a model can do vision in the llm_models table (#725)
* FEATURE: Track if a model can do vision in the llm_models table

* Data migration
2024-07-24 16:29:47 -03:00
Jan Cernik 738cd99ad6
FIX: Add bottom spacing for the new topic map (#722) 2024-07-22 22:21:23 -03:00
Joffrey JAFFEUX e4145ad6a6
FIX: ace-editor is now in discourse bundle, not admin (#717) 2024-07-17 11:58:50 +02:00
Roman Rizzi f328b81c78
FIX: Make sure custom tool enums follow json-schema. (#718)
Enums didn't work as expected because we the dialect couldn't translate
them correctly. It doesn't understand what "enum_values" is.
2024-07-16 14:23:17 -03:00
Keegan George 08355ea5d8
FEATURE: Show post helper as bottom modal on mobile (#704) 2024-07-10 11:01:05 -07:00
Martin Brennan da6d70da8f
FEATURE: Add breadcrumbs to LLMs and Persona admin pages (#666)
Followup to https://github.com/discourse/discourse-ai/pull/656,
adding these back in with the new core component.
2024-07-10 10:56:13 +10:00
Régis Hanol d555f18c6f
FIX: don't reset open state on details tag when morphing (#702) 2024-07-05 08:07:28 +10:00
Keegan George eab2f74b58
DEV: Use site locale for composer helper translations (#698) 2024-07-04 08:23:37 -07:00
Sam 1320eed9b2
FEATURE: move summary to use llm_model (#699)
This allows summary to use the new LLM models and migrates of API key based model selection

Claude 3.5 etc... all work now. 

---------

Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2024-07-04 10:48:18 +10:00
Keegan George ef4b3559cd
FIX: Disabled chat breaks `ai-chat-summarization` (#697) 2024-07-02 11:10:31 -07:00
Keegan George 1b0ba9197c
DEV: Add summarization logic from core (#658) 2024-07-02 08:51:59 -07:00
Sam b671ffe7fa
FIX: info not working, not suppressing hidden tags from report (#696)
2 small fixes

1. The info button was not properly working post refactor
2. Suppress any secured tags from report input
2024-07-02 16:38:33 +10:00
Jarek Radosz a5a39dd2ee
DEV: Clean up after #677 (#694)
Follow up to b863ddc94b

Ruby:
* Validate `summary` (the column is `not null`)
* Fix `name` validation (the column has `max_length` 100)
* Fix table annotations
* Accept missing `parameter` attributes (`required, `enum`, `enum_values`)

JS:
* Use native classes
* Don't use ember's array extensions
* Add explicit service injections
* Correct class names
* Use `||=` operator
* Use `store` service to create records
* Remove unused service injections
* Extract consts
* Group actions together
* Use `async`/`await`
* Use `withEventValue`
* Sort html attributes
* Use DButtons `@label` arg
* Use `input` elements instead of Ember's `Input` component (same w/ textarea)
* Remove `btn-default` class (automatically applied by DButton)
* Don't mix `I18n.t` and `i18n` in the same template
* Don't track props that aren't used in a template
* Correct invalid `target.value` code
* Remove unused/invalid `this.parameter`/`onChange` code
* Whitespace
* Use the new service import `inject as service` -> `service`
* Use `Object.entries()`
* Add missing i18n strings
* Fix an error in `addEnumValue` (calling `pushObject` on `undefined`)
* Use `TrackedArray`/`TrackedObject`
* Transform tool `parameters` keys (`enumValues` -> `enum_values`)
2024-06-28 08:59:51 +10:00
Sam b863ddc94b
FEATURE: custom user defined tools (#677)
Introduces custom AI tools functionality. 

1. Why it was added:
   The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform.

2. What it does:
   - Introduces a new `AiTool` model for storing custom AI tools
   - Adds CRUD (Create, Read, Update, Delete) operations for AI tools
   - Implements a tool runner system for executing custom tool scripts
   - Integrates custom tools with existing AI personas
   - Provides a user interface for managing custom tools in the admin panel

3. Possible use cases:
   - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...)
   - Allowing administrators to add new functionalities to AI assistants without modifying core code
   - Implementing domain-specific tools for particular communities or industries

4. Code structure:
   The PR introduces several new files and modifies existing ones:

   a. Models:
      - `app/models/ai_tool.rb`: Defines the AiTool model
      - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools

   b. Controllers:
      - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools

   c. Views and Components:
      - New Ember.js components for tool management in the admin interface
      - Updates to existing AI persona management components to support custom tools 

   d. Core functionality:
      - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system
      - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class

   e. Routes and configurations:
      - Updates to route configurations to include new AI tool management pages

   f. Migrations:
      - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table

   g. Tests:
      - New test files for AI tool functionality and integration

The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools.

Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs.

Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 17:27:40 +10:00
Roman Rizzi f622e2644f
FEATURE: Store provider-specific parameters. (#686)
Previously, we stored request parameters like the OpenAI organization and Bedrock's access key and region as site settings. This change stores them in the `llm_models` table instead, letting us drop more settings while also becoming more flexible.
2024-06-25 08:26:30 +10:00
Sam e04a7be122
FEATURE: LLM presets for model creation (#681)
* FEATURE: LLM presets for model creation

Previous to this users needed to look up complicated settings
when setting up models.

This introduces and extensible preset system with Google/OpenAI/Anthropic
presets.

This will cover all the most common LLMs, we can always add more as
we go.

Additionally:

- Proper support for Anthropic Claude Sonnet 3.5
- Stop blurring api keys when navigating away - this made it very complex to reuse keys
2024-06-21 17:32:15 +10:00
Rafael dos Santos Silva b23a3a86a6
FIX: SRV warning should not trigger on brand new LLM (#679) 2024-06-20 15:37:14 -03:00
Kris 1a8532b91b
UX: improve composer suggestion button layout (#678) 2024-06-20 13:32:14 -04:00
Kris 59ed6d7b3e
UX: show image caption button on image hover (#670) 2024-06-20 08:58:19 +10:00
Roman Rizzi ed3d5521a8
UX: QoL impromevements to the admin LLM models page. (#674)
API Key value is secret by default, and we include a link to the AI bot user.
2024-06-19 11:21:21 -03:00
Roman Rizzi c4d9fab8e7
FIX: typo when excluding personas from enabled bot list (#671) 2024-06-19 10:16:00 -03:00
Sam 0d6d9a6ef5
FEATURE: allow access to private topics if tool permits (#673)
Previously read tool only had access to public topics, this allows
access to all topics user has access to, if admin opts for the option
Also

- Fixes VLLM migration
- Display which llms have bot enabled
2024-06-19 15:49:36 +10:00
Roman Rizzi 8d5f901a67
DEV: Rewire AI bot internals to use LlmModel (#638)
* DRAFT: Create AI Bot users dynamically and support custom LlmModels

* Get user associated to llm_model

* Track enabled bots with attribute

* Don't store bot username. Minor touches to migrate default values in settings

* Handle scenario where vLLM uses a SRV record

* Made 3.5-turbo-16k the default version so we can remove hack
2024-06-18 14:32:14 -03:00
Sam 52a7dd2a4b
FEATURE: optional tool detail blocks (#662)
This is a rather huge refactor with 1 new feature (tool details can
be suppressed)

Previously we use the name "Command" to describe "Tools", this unifies
all the internal language and simplifies the code.

We also amended the persona UI to use less DToggles which aligns
with our design guidelines.

Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-11 18:14:14 +10:00
Martin Brennan 7a64699314
DEV: Remove breadcrumbs for now (#656)
This core PR will change the component API a bit,
so it's easier to remove these for now and add them
back after:

https://github.com/discourse/discourse/pull/27365
2024-06-07 10:37:53 +10:00
Keegan George 02a50a29f8
DEV: Conditionally show AI results toggle based on sort order (#652) 2024-05-29 18:18:22 -07:00
Keegan George dae9d6f14e
FIX: Move image caption group check logic to server side (#645)
* FIX: User groups error before initialization
* DEV: Move group check logic to server side
2024-05-28 10:29:11 +10:00
Keegan George 71affe75bf
UX: Hide AI preferences page completely if no settings for user (#644) 2024-05-27 13:27:45 -07:00
Roman Rizzi 333b331eb9
FEATURE: Allow deleting custom LLMs. (#643)
This change allows us to delete custom models. It checks if there is no module using them.

It also fixes a bug where the after-create transition wasn't working. While this prevents a model from being saved multiple times, endpoint validations are still needed (will be added in a separate PR).:
2024-05-27 16:44:08 -03:00
Keegan George 90c5e4bb0e
FIX: Reply broken when auto caption is enabled (#642) 2024-05-27 12:17:35 -07:00
Keegan George a1c649965f
FEATURE: Auto image captions (#637) 2024-05-27 10:49:24 -07:00
Sam f8381c0e8a
UX: suppress "this is a warning" (#636)
When triggering a PM from new-message route, we still had the UI
for "this is an official warning"

This removes that UI from bot messages, which is all clutter.
2024-05-23 12:55:33 +08:00
Martin Brennan 06137ac706
FEATURE: Use DBreadcrumbsItem in admin UI (#631)
This commit uses the new DBreadcrumbsItem and DBreadcrumbsContainer
from core to show a path back to the admin plugins list.
2024-05-22 09:19:53 +10:00
Keegan George 59e63a2da9
FIX: Unresponsive post buttons due to Ask AI highlight (#635) 2024-05-21 13:58:37 -07:00
Roman Rizzi 3a9080dd14
FEATURE: Test LLM configuration (#634) 2024-05-21 13:35:50 -03:00
Roman Rizzi d8ebed8fb5
UX: Follow plugin user interface UI guidelines. (#628) 2024-05-16 14:28:57 -03:00
Roman Rizzi 1d786fbaaf
FEATURE: Set endpoint credentials directly from LlmModel. (#625)
* FEATURE: Set endpoint credentials directly from LlmModel.

Drop Llama2Tokenizer since we no longer use it.

* Allow http for custom LLMs

---------

Co-authored-by: Rafael Silva <xfalcox@gmail.com>
2024-05-16 09:50:22 -03:00
Régis Hanol 1e6d9ed634
FIX: respect "external_links_in_new_tab" user preference... (#622)
... for AI conversations since they look & feel "external".

Internal ref - /t/128182
2024-05-15 10:06:38 +02:00
Jarek Radosz fc73cce113
FIX: Invalid header button title (#621)
`[en.Start a PM with an AI bot]`
2024-05-14 15:30:03 +02:00
Sam cb23ae614f
UX: Remove multi llm selector from header and move to composer (#619)
LLM selector control had no memory and was awkward to click.

Instead we now:

- Clearly display which llm you are talking to
- Allow you to change llm direct from composer
2024-05-14 17:54:54 +10:00
Roman Rizzi 62fc7d6ed0
FEATURE: Configurable LLMs. (#606)
This PR introduces the concept of "LlmModel" as a new way to quickly add new LLM models without making any code changes. We are releasing this first version and will add incremental improvements, so expect changes.

The AI Bot can't fully take advantage of this feature as users are hard-coded. We'll fix this in a separate PR.s
2024-05-13 12:46:42 -03:00
Joffrey JAFFEUX 64f41454ad
FIX: uses getByIdentifier of d-menu (#611)
The menu service doesn’t implement an activeMenu property anymore as it can now support concurrent menus. The solution to this is to use `getByIdentifier`.
2024-05-10 12:01:02 +02:00
Sam 61890b667c
FEATURE: search command now support searching in context of user (#610)
This optional feature allows search to be performed in the context
of the user that executed it.

By default we do not allow this behavior cause it means llm gets
access to potentially secure data.
2024-05-10 11:32:34 +10:00
Sam 514823daca
FIX: streaming broken in bedrock when chunks are not aligned (#609)
Also

- Stop caching llm list - this cause llm list in persona to be incorrect
- Add more UI to debug screen so you can properly see raw response
2024-05-09 12:11:50 +10:00
Sam 37a2db5223
FIX: uploader not removing app event (#601)
FIX: restricted to mentionabled vs allowed_chat by mistake
2024-05-06 14:42:55 +10:00
Sam e4b326c711
FEATURE: support Chat with AI Persona via a DM (#488)
Add support for chat with AI personas

- Allow enabling chat for AI personas that have an associated user
- Add new setting `allow_chat` to AI persona to enable/disable chat
- When a message is created in a DM channel with an allowed AI persona user, schedule a reply job
- AI replies to chat messages using the persona's `max_context_posts` setting to determine context
- Store tool calls and custom prompts used to generate a chat reply on the `ChatMessageCustomPrompt` table
- Add tests for AI chat replies with tools and context

At the moment unlike posts we do not carry tool calls in the context.

No @mention support yet for ai personas in channels, this is future work
2024-05-06 09:49:02 +10:00
Keegan George 8875830f6a
FEATURE: Insert footnote from explained result (#591) 2024-05-03 11:53:17 -07:00
Martin Brennan b52d3c7d29
DEV: Moving around admin persona config routes again (#586)
The initial setup done in fb0d56324f
clashed with other plugins, I found this when trying to do the same
for Gamification. This uses a better routing setup and removes the
need to define the config nav link for Settings -- that is always inserted.

Relies on https://github.com/discourse/discourse/pull/26707
2024-05-02 12:42:30 +10:00
Sam 32b3004ce9
FEATURE: Add Question Consolidator for robust Upload support in Personas (#596)
This commit introduces a new feature for AI Personas called the "Question Consolidator LLM". The purpose of the Question Consolidator is to consolidate a user's latest question into a self-contained, context-rich question before querying the vector database for relevant fragments. This helps improve the quality and relevance of the retrieved fragments.

Previous to this change we used the last 10 interactions, this is not ideal cause the RAG would "lock on" to an answer. 

EG:

- User: how many cars are there in europe
- Model: detailed answer about cars in europe including the term car and vehicle many times
- User: Nice, what about trains are there in the US

In the above example "trains" and "US" becomes very low signal given there are pages and pages talking about cars and europe. This mean retrieval is sub optimal. 

Instead, we pass the history to the "question consolidator", it would simply consolidate the question to "How many trains are there in the United States", which would make it fare easier for the vector db to find relevant content. 

The llm used for question consolidator can often be less powerful than the model you are talking to, we recommend using lighter weight and fast models cause the task is very simple. This is configurable from the persona ui.

This PR also removes support for {uploads} placeholder, this is too complicated to get right and we want freedom to shift RAG implementation. 

Key changes:

1. Added a new `question_consolidator_llm` column to the `ai_personas` table to store the LLM model used for question consolidation.

2. Implemented the `QuestionConsolidator` module which handles the logic for consolidating the user's latest question. It extracts the relevant user and model messages from the conversation history, truncates them if needed to fit within the token limit, and generates a consolidated question prompt.

3. Updated the `Persona` class to use the Question Consolidator LLM (if configured) when crafting the RAG fragments prompt. It passes the conversation context to the consolidator to generate a self-contained question.

4. Added UI elements in the AI Persona editor to allow selecting the Question Consolidator LLM. Also made some UI tweaks to conditionally show/hide certain options based on persona configuration.

5. Wrote unit tests for the QuestionConsolidator module and updated existing persona tests to cover the new functionality.

This feature enables AI Personas to better understand the context and intent behind a user's question by consolidating the conversation history into a single, focused question. This can lead to more relevant and accurate responses from the AI assistant.
2024-04-30 13:49:21 +10:00
Roman Rizzi 283445cf81
FIX: RAG uploader must support multi-file indexing. (#592)
Updating the editing model's rag_uploads in the editor component broke multi-file uploading. Instead, we'll keep the uploads in the uploader and update the model when we finish.

This PR also fast-tracks the initial update so we can show feedback to the user quickly, and allows uploading MD files.

Bug reported on https://meta.discourse.org/t/discourse-ai-persona-upload-support/304049/11
2024-04-25 10:48:55 -03:00
Sam 4a29f8ed1c
FEATURE: Enhance AI debugging capabilities and improve interface adjustments (#577)
* FIX: various RAG edge cases

- Nicer text to describe RAG, avoids the word RAG
- Do not attempt to save persona when removing uploads and it is not created
- Remove old code that avoided touching rag params on create

* FIX: Missing pause button for persona users

* Feature: allow specific users to debug ai request / response chains

This can help users easily tune RAG and figure out what is going
on with requests.

* discourse helper so it does not explode

* fix test

* simplify implementation
2024-04-15 23:22:06 +10:00
Sam f6ac5cd0a8
FEATURE: allow tuning of RAG generation (#565)
* FEATURE: allow tuning of RAG generation

- change chunking to be token based vs char based (which is more accurate)
- allow control over overlap / tokens per chunk and conversation snippets inserted
- UI to control new settings

* improve ui a bit

* fix various reindex issues

* reduce concurrency

* try ultra low queue ... concurrency 1 is too slow.
2024-04-12 10:32:46 -03:00
Keegan George 8444789974
UX: Update suggestion radii to accommodate for new default (#564) 2024-04-09 10:48:18 -07:00
Roman Rizzi aa8918911d
UX: Display the indexing progress for RAG uploads (#557) 2024-04-09 11:03:07 -03:00
Keegan George 35fbf5c836
FIX: Ask AI highlight fixes (#562) 2024-04-08 11:00:03 -07:00