Commit Graph

962 Commits

Author SHA1 Message Date
Roman Rizzi acc3f817e1
UX: Clarify purpose of OpenAI API key setting () 2024-08-02 15:57:40 -03:00
Sam 948cf893a9
FIX: Add tool support to open ai compatible dialect and vllm ()
* FIX: Add tool support to open ai compatible dialect and vllm

Automatic tools are in progress in vllm see: https://github.com/vllm-project/vllm/pull/5649

Even when they are supported, initial support will be uneven, only some models have native tool support
notably mistral which has some special tokens for tool support.

After the above PR lands in vllm we will still need to swap to
XML based tools on models without native tool support.

* fix specs
2024-08-02 09:52:33 -03:00
Natalie Tay b7ac229547
DEV: Pin plugin for Discourse < 3.4.0.beta1-dev () 2024-08-02 17:03:27 +08:00
Rafael dos Santos Silva 7dc0a2a20a
DEV: Log error responses on Gemini / Cloudflare embeddings requests () 2024-08-01 17:25:24 -03:00
Rafael dos Santos Silva 9d887ad4ac
FIX: Use correct date for cached summary () 2024-07-31 15:21:26 -03:00
Rafael dos Santos Silva d4c90bc2ba
FEATURE: Make emotion analysis enabled by default () 2024-07-31 12:00:00 -03:00
Sam c16c622b53
FIX: properly pass errors to client ()
render_json_error expects a AR model not a serializer, using a
serializer eats up the error message
2024-07-31 17:53:18 +10:00
Roman Rizzi bed044448c
DEV: Remove old code now that features rely on LlmModels. ()
* 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
Discourse Translator Bot 73a2b15e91
Update translations () 2024-07-30 11:08:03 -03:00
Natalie Tay 7cd7f71857
DEV: Promote historical post-deploy migrations () 2024-07-30 01:44:57 +08:00
Rafael dos Santos Silva 665637fbad
FIX: Properly fix ai_summaries table sequence ()
* FIX: Properly fix ai_summaries table sequence

Previous attempt at 3815360 could fail due to a race introduced in 1b0ba91 where summaries are migrated to core in a post_migrate erroneously.
2024-07-26 14:45:01 -03:00
Jan Cernik d58913b227
FIX: Collapse `Summarize` button on mobile () 2024-07-25 16:10:53 -03:00
Jan Cernik d9dad56c6a
UX: Use `DMenu` for topic summarization () 2024-07-25 10:47:18 -03:00
Roman Rizzi 5c196bca89
FEATURE: Track if a model can do vision in the llm_models table ()
* FEATURE: Track if a model can do vision in the llm_models table

* Data migration
2024-07-24 16:29:47 -03:00
Discourse Translator Bot 06e239321b
Update translations () 2024-07-23 15:23:51 +02:00
Jan Cernik 738cd99ad6
FIX: Add bottom spacing for the new topic map () 2024-07-22 22:21:23 -03:00
Rafael dos Santos Silva 3502f0f1cd
FEATURE: GPT4o Tokenizer () 2024-07-22 15:26:14 -03:00
Roman Rizzi 7f2c3a1ab9
DEV: Pin plugin for v3.2 to guarantee Ruby 3.3 compat () 2024-07-17 13:16:14 -03:00
Joffrey JAFFEUX e4145ad6a6
FIX: ace-editor is now in discourse bundle, not admin () 2024-07-17 11:58:50 +02:00
Discourse Translator Bot 4d8090002f
Update translations () 2024-07-16 22:14:09 +02:00
Roman Rizzi f328b81c78
FIX: Make sure custom tool enums follow json-schema. ()
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
Roman Rizzi 0a8195242b
FIX: Limit system message size to 60% of available tokens. ()
Using RAG fragments can lead to considerably big system messages, which becomes problematic when models have a smaller context window.

Before this change, we only look at the rest of the conversation to make sure we don't surpass the limit, which could lead to two unwanted scenarios when having large system messages:

All other messages are excluded due to size.
The system message already exceeds the limit.

As a result, I'm putting a hard-limit of 60% of available tokens. We don't want to aggresively truncate because if rag fragments are included, the system message contains a lot of context to improve the model response, but we also want to make room for the recent messages in the conversation.
2024-07-12 15:09:01 -03:00
Martin Brennan 5c1ab85583
DEV: More topic title prompt tweaks ()
Followup 8d4a67fbe2

The prompt worked better, but it took the instructions
about never using lowercase a little too literally,
it wasn't using it for things like LLM or Discourse,
also it was almost always framing the title as questions
so now I asked it for a mix of questions and statements
because that's less ambiguous.
2024-07-11 10:14:53 +10:00
Keegan George 08355ea5d8
FEATURE: Show post helper as bottom modal on mobile () 2024-07-10 11:01:05 -07:00
Martin Brennan 8d4a67fbe2
DEV: Tweak topic title generator prompt ()
Changes the title generator prompt to avoid clickbait-y
titles and also try to avoid AI's favourite title format,
which is "Some Thing: Other Thing"

Leaving the chat thread title generator for now, that's
not as important, the bizarre titles add to the experience there.
2024-07-10 14:31:59 +10:00
Martin Brennan da6d70da8f
FEATURE: Add breadcrumbs to LLMs and Persona admin pages ()
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
Discourse Translator Bot 84b1c9af71
Update translations () 2024-07-09 23:12:11 +02:00
Roman Rizzi 5cb91217bd
FIX: Flaky SRV-backed model seeding. ()
* Seeding the SRV-backed model should happen inside an initializer.
* Keep the model up to date when the hidden setting changes.
* Use the correct Mixtral model name and fix previous data migration.
* URL validation should trigger only when we attempt to update it.
2024-07-08 18:47:10 -03:00
PangBo 4ebbdc043e
fix: locale handling in assistant.rb () 2024-07-05 11:16:09 +02:00
Régis Hanol d555f18c6f
FIX: don't reset open state on details tag when morphing () 2024-07-05 08:07:28 +10:00
Roman Rizzi 442681a3d3
FIX: Mixtral models have system role support. ()
Using assistant role for system produces an error because
they expect alternating roles like user/assistant/user and so on.
Prompts cannot start with the assistant role.
2024-07-04 13:23:03 -03:00
Keegan George eab2f74b58
DEV: Use site locale for composer helper translations () 2024-07-04 08:23:37 -07:00
Sam 38153608f8
FIX: repair id sequence identity on summary table ()
1. Repairs the identity on the summary table, we migrated data without resetting it.
2. Adds an index into ai_summary table to match expected retrieval pattern
2024-07-04 12:23:46 +10:00
Sam 1320eed9b2
FEATURE: move summary to use llm_model ()
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
Roman Rizzi fc081d9da6
FIX: Restore ability to fold summaries, which was accidentally removed () 2024-07-03 18:10:31 -03:00
Keegan George ef4b3559cd
FIX: Disabled chat breaks `ai-chat-summarization` () 2024-07-02 11:10:31 -07:00
Keegan George 1b0ba9197c
DEV: Add summarization logic from core () 2024-07-02 08:51:59 -07:00
Discourse Translator Bot c352cc5ba3
Update translations () 2024-07-02 16:42:52 +02:00
Sam b671ffe7fa
FIX: info not working, not suppressing hidden tags from report ()
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 ()
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
Rafael dos Santos Silva a708d4dfa2
FIX: Use base64 encoded images in AI Image Caption via LLaVa ()
* FIX: Use base64 encoded images in AI Image Caption via LLaVa

This fixed a regression introduced in  where we started sending
schemaless URLs for our LLaVa service, which doesn't handle it well.

Moving to base64 encoded images solves:

- The service needing to download images
  Now the service running LLaVa doesn't need internet access

- Secure uploads compat
  Every image is treated the same, less branching for secure uploads

- Image Size problems
  Discourse is now responsible for ensure a max size for images

- Troublesome dev env
  Previously to this commit you would need a dev env that was internet
acessible to use llava image captions
2024-06-27 16:24:44 -03:00
Jan Cernik 8e83c091a2
DEV: Use explicit serializers for all models () 2024-06-27 10:43:00 -03:00
Sam b863ddc94b
FEATURE: custom user defined tools ()
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
Sam af4f871096
FIX: never provide tools with invalid UTF-8 strings ()
Previous to this change, on truncation we could return invalid
UTF-8 strings to caller

This also allows tools to read up to 30 megs vs the old 4 megs.
2024-06-27 14:06:52 +10:00
Loïc Guitaut e26c5986f2 DEV: Use Rails 7.0 instead of 7.1 in post-migrations 2024-06-26 18:41:38 +02:00
Loïc Guitaut 6f5873b072 DEV: Use Rails 7.0 instead of 7.1 in migrations 2024-06-26 18:32:11 +02:00
Roman Rizzi e39e0bdb4a
FIX: Move the bot user toggling to the controller. ()
Having this as a callback prevents deploys of sites with a vLLM SRV configured and pending migrations. Additionally, this fixes a bug where we didn't delete/deactivate the companion user after deleting an LLM.
2024-06-25 12:45:19 -03:00
Discourse Translator Bot b6f0ad157c
Update translations () 2024-06-25 15:40:17 +02:00
Roman Rizzi f622e2644f
FEATURE: Store provider-specific parameters. ()
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 1d5fa0ce6c
FIX: when creating an llm we were not creating user ()
This meant that if you toggle ai user early it surprisingly did
not work.

Also remove safety settings from gemini, it is overly cautious
2024-06-24 09:59:42 +10:00