* DEV: Use structured responses for summaries
* Fix system specs
* Make response_format a first class citizen and update endpoints to support it
* Response format can be specified in the persona
* lint
* switch to jsonb and make column nullable
* Reify structured output chunks. Move JSON parsing to the depths of Completion
* Switch to JsonStreamingTracker for partial JSON parsing
adds support for "thinking tokens" - a feature that exposes the model's reasoning process before providing the final response. Key improvements include:
- Add a new Thinking class to handle thinking content from LLMs
- Modify endpoints (Claude, AWS Bedrock) to handle thinking output
- Update AI bot to display thinking in collapsible details section
- Fix SEARCH/REPLACE blocks to support empty replacement strings and general improvements to artifact editing
- Allow configurable temperature in triage and report automations
- Various bug fixes and improvements to diff parsing
This PR introduces several enhancements and refactorings to the AI Persona and RAG (Retrieval-Augmented Generation) functionalities within the discourse-ai plugin. Here's a breakdown of the changes:
**1. LLM Model Association for RAG and Personas:**
- **New Database Columns:** Adds `rag_llm_model_id` to both `ai_personas` and `ai_tools` tables. This allows specifying a dedicated LLM for RAG indexing, separate from the persona's primary LLM. Adds `default_llm_id` and `question_consolidator_llm_id` to `ai_personas`.
- **Migration:** Includes a migration (`20250210032345_migrate_persona_to_llm_model_id.rb`) to populate the new `default_llm_id` and `question_consolidator_llm_id` columns in `ai_personas` based on the existing `default_llm` and `question_consolidator_llm` string columns, and a post migration to remove the latter.
- **Model Changes:** The `AiPersona` and `AiTool` models now `belong_to` an `LlmModel` via `rag_llm_model_id`. The `LlmModel.proxy` method now accepts an `LlmModel` instance instead of just an identifier. `AiPersona` now has `default_llm_id` and `question_consolidator_llm_id` attributes.
- **UI Updates:** The AI Persona and AI Tool editors in the admin panel now allow selecting an LLM for RAG indexing (if PDF/image support is enabled). The RAG options component displays an LLM selector.
- **Serialization:** The serializers (`AiCustomToolSerializer`, `AiCustomToolListSerializer`, `LocalizedAiPersonaSerializer`) have been updated to include the new `rag_llm_model_id`, `default_llm_id` and `question_consolidator_llm_id` attributes.
**2. PDF and Image Support for RAG:**
- **Site Setting:** Introduces a new hidden site setting, `ai_rag_pdf_images_enabled`, to control whether PDF and image files can be indexed for RAG. This defaults to `false`.
- **File Upload Validation:** The `RagDocumentFragmentsController` now checks the `ai_rag_pdf_images_enabled` setting and allows PDF, PNG, JPG, and JPEG files if enabled. Error handling is included for cases where PDF/image indexing is attempted with the setting disabled.
- **PDF Processing:** Adds a new utility class, `DiscourseAi::Utils::PdfToImages`, which uses ImageMagick (`magick`) to convert PDF pages into individual PNG images. A maximum PDF size and conversion timeout are enforced.
- **Image Processing:** A new utility class, `DiscourseAi::Utils::ImageToText`, is included to handle OCR for the images and PDFs.
- **RAG Digestion Job:** The `DigestRagUpload` job now handles PDF and image uploads. It uses `PdfToImages` and `ImageToText` to extract text and create document fragments.
- **UI Updates:** The RAG uploader component now accepts PDF and image file types if `ai_rag_pdf_images_enabled` is true. The UI text is adjusted to indicate supported file types.
**3. Refactoring and Improvements:**
- **LLM Enumeration:** The `DiscourseAi::Configuration::LlmEnumerator` now provides a `values_for_serialization` method, which returns a simplified array of LLM data (id, name, vision_enabled) suitable for use in serializers. This avoids exposing unnecessary details to the frontend.
- **AI Helper:** The `AiHelper::Assistant` now takes optional `helper_llm` and `image_caption_llm` parameters in its constructor, allowing for greater flexibility.
- **Bot and Persona Updates:** Several updates were made across the codebase, changing the string based association to a LLM to the new model based.
- **Audit Logs:** The `DiscourseAi::Completions::Endpoints::Base` now formats raw request payloads as pretty JSON for easier auditing.
- **Eval Script:** An evaluation script is included.
**4. Testing:**
- The PR introduces a new eval system for LLMs, this allows us to test how functionality works across various LLM providers. This lives in `/evals`
### Why
This pull request fundamentally restructures how AI bots create and update web artifacts to address critical limitations in the previous approach:
1. **Improved Artifact Context for LLMs**: Previously, artifact creation and update tools included the *entire* artifact source code directly in the tool arguments. This overloaded the Language Model (LLM) with raw code, making it difficult for the LLM to maintain a clear understanding of the artifact's current state when applying changes. The LLM would struggle to differentiate between the base artifact and the requested modifications, leading to confusion and less effective updates.
2. **Reduced Token Usage and History Bloat**: Including the full artifact source code in every tool interaction was extremely token-inefficient. As conversations progressed, this redundant code in the history consumed a significant number of tokens unnecessarily. This not only increased costs but also diluted the context for the LLM with less relevant historical information.
3. **Enabling Updates for Large Artifacts**: The lack of a practical diff or targeted update mechanism made it nearly impossible to efficiently update larger web artifacts. Sending the entire source code for every minor change was both computationally expensive and prone to errors, effectively blocking the use of AI bots for meaningful modifications of complex artifacts.
**This pull request addresses these core issues by**:
* Introducing methods for the AI bot to explicitly *read* and understand the current state of an artifact.
* Implementing efficient update strategies that send *targeted* changes rather than the entire artifact source code.
* Providing options to control the level of artifact context included in LLM prompts, optimizing token usage.
### What
The main changes implemented in this PR to resolve the above issues are:
1. **`Read Artifact` Tool for Contextual Awareness**:
- A new `read_artifact` tool is introduced, enabling AI bots to fetch and process the current content of a web artifact from a given URL (local or external).
- This provides the LLM with a clear and up-to-date representation of the artifact's HTML, CSS, and JavaScript, improving its understanding of the base to be modified.
- By cloning local artifacts, it allows the bot to work with a fresh copy, further enhancing context and control.
2. **Refactored `Update Artifact` Tool with Efficient Strategies**:
- The `update_artifact` tool is redesigned to employ more efficient update strategies, minimizing token usage and improving update precision:
- **`diff` strategy**: Utilizes a search-and-replace diff algorithm to apply only the necessary, targeted changes to the artifact's code. This significantly reduces the amount of code sent to the LLM and focuses its attention on the specific modifications.
- **`full` strategy**: Provides the option to replace the entire content sections (HTML, CSS, JavaScript) when a complete rewrite is required.
- Tool options enhance the control over the update process:
- `editor_llm`: Allows selection of a specific LLM for artifact updates, potentially optimizing for code editing tasks.
- `update_algorithm`: Enables choosing between `diff` and `full` update strategies based on the nature of the required changes.
- `do_not_echo_artifact`: Defaults to true, and by *not* echoing the artifact in prompts, it further reduces token consumption in scenarios where the LLM might not need the full artifact context for every update step (though effectiveness might be slightly reduced in certain update scenarios).
3. **System and General Persona Tool Option Visibility and Customization**:
- Tool options, including those for system personas, are made visible and editable in the admin UI. This allows administrators to fine-tune the behavior of all personas and their tools, including setting specific LLMs or update algorithms. This was previously limited or hidden for system personas.
4. **Centralized and Improved Content Security Policy (CSP) Management**:
- The CSP for AI artifacts is consolidated and made more maintainable through the `ALLOWED_CDN_SOURCES` constant. This improves code organization and future updates to the allowed CDN list, while maintaining the existing security posture.
5. **Codebase Improvements**:
- Refactoring of diff utilities, introduction of strategy classes, enhanced error handling, new locales, and comprehensive testing all contribute to a more robust, efficient, and maintainable artifact management system.
By addressing the issues of LLM context confusion, token inefficiency, and the limitations of updating large artifacts, this pull request significantly improves the practicality and effectiveness of AI bots in managing web artifacts within Discourse.
* DEV: raise timeout for reasoning LLMs
* FIX: use id to identify llms, not model_name
model_name is not unique, in the case of reasoning models
you may configure the same llm multiple times using different
reasoning levels.
Adds a comprehensive quota management system for LLM models that allows:
- Setting per-group (applied per user in the group) token and usage limits with configurable durations
- Tracking and enforcing token/usage limits across user groups
- Quota reset periods (hourly, daily, weekly, or custom)
- Admin UI for managing quotas with real-time updates
This system provides granular control over LLM API usage by allowing admins
to define limits on both total tokens and number of requests per group.
Supports multiple concurrent quotas per model and automatically handles
quota resets.
Co-authored-by: Keegan George <kgeorge13@gmail.com>
Disabling streaming is required for models such o1 that do not have streaming
enabled yet
It is good to carry this feature around in case various apis decide not to support streaming endpoints and Discourse AI can continue to work just as it did before.
Also: fixes issue where sharing artifacts would miss viewport leading to tiny artifacts on mobile
* FEATURE: first class support for OpenRouter
This new implementation supports picking quantization and provider pref
Also:
- Improve logging for summary generation
- Improve error message when contacting LLMs fails
* Better support for full screen artifacts on iPad
Support back button to close full screen
This is a significant PR that introduces AI Artifacts functionality to the discourse-ai plugin along with several other improvements. Here are the key changes:
1. AI Artifacts System:
- Adds a new `AiArtifact` model and database migration
- Allows creation of web artifacts with HTML, CSS, and JavaScript content
- Introduces security settings (`strict`, `lax`, `disabled`) for controlling artifact execution
- Implements artifact rendering in iframes with sandbox protection
- New `CreateArtifact` tool for AI to generate interactive content
2. Tool System Improvements:
- Adds support for partial tool calls, allowing incremental updates during generation
- Better handling of tool call states and progress tracking
- Improved XML tool processing with CDATA support
- Fixes for tool parameter handling and duplicate invocations
3. LLM Provider Updates:
- Updates for Anthropic Claude models with correct token limits
- Adds support for native/XML tool modes in Gemini integration
- Adds new model configurations including Llama 3.1 models
- Improvements to streaming response handling
4. UI Enhancements:
- New artifact viewer component with expand/collapse functionality
- Security controls for artifact execution (click-to-run in strict mode)
- Improved dialog and response handling
- Better error management for tool execution
5. Security Improvements:
- Sandbox controls for artifact execution
- Public/private artifact sharing controls
- Security settings to control artifact behavior
- CSP and frame-options handling for artifacts
6. Technical Improvements:
- Better post streaming implementation
- Improved error handling in completions
- Better memory management for partial tool calls
- Enhanced testing coverage
7. Configuration:
- New site settings for artifact security
- Extended LLM model configurations
- Additional tool configuration options
This PR significantly enhances the plugin's capabilities for generating and displaying interactive content while maintaining security and providing flexible configuration options for administrators.
Implement streaming tool call implementation for Anthropic and Open AI.
When calling:
llm.generate(..., partial_tool_calls: true) do ...
Partials may contain ToolCall instances with partial: true, These tool calls are partially populated with json partially parsed.
So for example when performing a search you may get:
ToolCall(..., {search: "hello" })
ToolCall(..., {search: "hello world" })
The library used to parse json is:
https://github.com/dgraham/json-stream
We use a fork cause we need access to the internal buffer.
This prepares internals to perform partial tool calls, but does not implement it yet.
This re-implements tool support in DiscourseAi::Completions::Llm #generate
Previously tool support was always returned via XML and it would be the responsibility of the caller to parse XML
New implementation has the endpoints return ToolCall objects.
Additionally this simplifies the Llm endpoint interface and gives it more clarity. Llms must implement
decode, decode_chunk (for streaming)
It is the implementers responsibility to figure out how to decode chunks, base no longer implements. To make this easy we ship a flexible json decoder which is easy to wire up.
Also (new)
Better debugging for PMs, we now have a next / previous button to see all the Llm messages associated with a PM
Token accounting is fixed for vllm (we were not correctly counting tokens)
A new feature_context json column was added to ai_api_audit_logs
This allows us to store rich json like context on any LLM request
made.
This new field now stores automation id and name.
Additionally allows llm_triage to specify maximum number of tokens
This means that you can limit the cost of llm triage by scanning only
first N tokens of a post.
* 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.
Native tools do not work well on Opus.
Chain of Thought prompting means it consumes enormous amounts of
tokens and has poor latency.
This commit introduce and XML stripper to remove various chain of
thought XML islands from anthropic prompts when tools are involved.
This mean Opus native tools is now functions (albeit slowly)
From local testing XML just works better now.
Also fixes enum support in Anthropic native tools
* 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>
- Introduce new support for GPT4o (automation / bot / summary / helper)
- Properly account for token counts on OpenAI models
- Track feature that was used when generating AI completions
- Remove custom llm support for summarization as we need better interfaces to control registration and de-registration
There are still some limitations to which models we can support with the `LlmModel` class. This will enable support for Llama3 while we sort those out.
Both endpoints provide OpenAI-compatible servers. The only difference is that Vllm doesn't support passing tools as a separate parameter. Even if the tool param is supported, it ultimately relies on the model's ability to handle native functions, which is not the case with the models we have today.
As a part of this change, we are dropping support for StableBeluga/Llama2 models. They don't have a chat_template, meaning the new API can translate them.
These changes let us remove some of our existing dialects and are a first step in our plan to support any LLM by defining them as data-driven concepts.
I rewrote the "translate" method to use a template method and extracted the tool support strategies into its classes to simplify the code.
Finally, these changes bring support for Ollama when running in dev mode. It only works with Mistral for now, but it will change soon..
For quite a few weeks now, some times, when running function calls
on Anthropic we would get a "stray" - "calls" line.
This has been enormously frustrating!
I have been unable to find the source of the bug so instead decoupled
the implementation and create a very clear "function call normalizer"
This new class is extensively tested and guards against the type of
edge cases we saw pre-normalizer.
This also simplifies the implementation of "endpoint" which no longer
needs to handle all this complex logic.
- Added Cohere Command models (Command, Command Light, Command R, Command R Plus) to the available model list
- Added a new site setting `ai_cohere_api_key` for configuring the Cohere API key
- Implemented a new `DiscourseAi::Completions::Endpoints::Cohere` class to handle interactions with the Cohere API, including:
- Translating request parameters to the Cohere API format
- Parsing Cohere API responses
- Supporting streaming and non-streaming completions
- Supporting "tools" which allow the model to call back to discourse to lookup additional information
- Implemented a new `DiscourseAi::Completions::Dialects::Command` class to translate between the generic Discourse AI prompt format and the Cohere Command format
- Added specs covering the new Cohere endpoint and dialect classes
- Updated `DiscourseAi::AiBot::Bot.guess_model` to map the new Cohere model to the appropriate bot user
In summary, this PR adds support for using the Cohere Command family of models with the Discourse AI plugin. It handles configuring API keys, making requests to the Cohere API, and translating between Discourse's generic prompt format and Cohere's specific format. Thorough test coverage was added for the new functionality.
This PR consolidates the implements new Anthropic Messages interface for Bedrock Claude endpoints and adds support for the new Claude 3 models (haiku, opus, sonnet).
Key changes:
- Renamed `AnthropicMessages` and `Anthropic` endpoint classes into a single `Anthropic` class (ditto for ClaudeMessages -> Claude)
- Updated `AwsBedrock` endpoints to use the new `/messages` API format for all Claude models
- Added `claude-3-haiku`, `claude-3-opus` and `claude-3-sonnet` model support in both Anthropic and AWS Bedrock endpoints
- Updated specs for the new consolidated endpoints and Claude 3 model support
This refactor removes support for old non messages API which has been deprecated by anthropic
Introduces a new AI Bot persona called 'GitHub Helper' which is specialized in assisting with GitHub-related tasks and questions. It includes the following key changes:
- Implements the GitHub Helper persona class with its system prompt and available tools
- Adds three new AI Bot tools for GitHub interactions:
- github_file_content: Retrieves content of files from a GitHub repository
- github_pull_request_diff: Retrieves the diff for a GitHub pull request
- github_search_code: Searches for code in a GitHub repository
- Updates the AI Bot dialects to support the new GitHub tools
- Implements multiple function calls for standard tool dialect
This provides new support for messages API from Claude.
It is required for latest model access.
Also corrects implementation of function calls.
* Fix message interleving
* fix broken spec
* add new models to automation
* FIX: support multiple tool calls
Prior to this change we had a hard limit of 1 tool call per llm
round trip. This meant you could not google multiple things at
once or perform searches across two tools.
Also:
- Hint when Google stops working
- Log topic_id / post_id when performing completions
* Also track id for title
The Faraday adapter and `FinalDestionation::HTTP` will protect us from admin-initiated SSRF attacks when interacting with the external services powering this plugin features.:
When bedrock rate limits it returns a 200 BUT also returns a JSON
document with the error.
Previously we had no special case here so we complained about nil
New code properly logs the problem
* UX: Validations to Llm-backed features (except AI Bot)
This change is part of an ongoing effort to prevent enabling a broken feature due to lack of configuration. We also want to explicit which provider we are going to use. For example, Claude models are available through AWS Bedrock and Anthropic, but the configuration differs.
Validations are:
* You must choose a model before enabling the feature.
* You must turn off the feature before setting the model to blank.
* You must configure each model settings before being able to select it.
* Add provider name to summarization options
* vLLM can technically support same models as HF
* Check we can talk to the selected model
* Check for Bedrock instead of anthropic as a site could have both creds setup
This PR introduces 3 things:
1. Fake bot that can be used on local so you can test LLMs, to enable on dev use:
SiteSetting.ai_bot_enabled_chat_bots = "fake"
2. More elegant smooth streaming of progress on LLM completion
This leans on JavaScript to buffer and trickle llm results through. It also amends it so the progress dot is much
more consistently rendered
3. It fixes the Claude dialect
Claude needs newlines **exactly** at the right spot, amended so it is happy
---------
Co-authored-by: Martin Brennan <martin@discourse.org>
It also corrects the syntax around tool support, which was wrong.
Gemini doesn't want us to include messages about previous tool invocations, so I had to shuffle around some code to send the response it generated from those invocations instead. For this, I created the "multi_turn" context, which bundles all the context involved in the interaction.
* DEV: AI bot migration to the Llm pattern.
We added tool and conversation context support to the Llm service in discourse-ai#366, meaning we met all the conditions to migrate this module.
This PR migrates to the new pattern, meaning adding a new bot now requires minimal effort as long as the service supports it. On top of this, we introduce the concept of a "Playground" to separate the PM-specific bits from the completion, allowing us to use the bot in other contexts like chat in the future. Commands are called tools, and we simplified all the placeholder logic to perform updates in a single place, making the flow more one-wayish.
* Followup fixes based on testing
* Cleanup unused inference code
* FIX: text-based tools could be in the middle of a sentence
* GPT-4-turbo support
* Use new LLM API
* FIX: AI helper not working correctly with mixtral
This PR introduces a new function on the generic llm called #generate
This will replace the implementation of completion!
#generate introduces a new way to pass temperature, max_tokens and stop_sequences
Then LLM implementers need to implement #normalize_model_params to
ensure the generic names match the LLM specific endpoint
This also adds temperature and stop_sequences to completion_prompts
this allows for much more robust completion prompts
* port everything over to #generate
* Fix translation
- On anthropic this no longer throws random "This is your translation:"
- On mixtral this actually works
* fix markdown table generation as well
Previously endpoint/base would `+=` decoded_chunk to leftover
This could lead to cases where the leftover buffer had duplicate
previously processed data
Fix ensures we properly skip previously decoded data.
This PR adds tool support to available LLMs. We'll buffer tool invocations and return them instead of making users of this service parse the response.
It also adds support for conversation context in the generic prompt. It includes bot messages, user messages, and tool invocations, which we'll trim to make sure it doesn't exceed the prompt limit, then translate them to the correct dialect.
Finally, It adds some buffering when reading chunks to handle cases when streaming is extremely slow.:M
Previous to this change we relied on explicit loading for a files in Discourse AI.
This had a few downsides:
- Busywork whenever you add a file (an extra require relative)
- We were not keeping to conventions internally ... some places were OpenAI others are OpenAi
- Autoloader did not work which lead to lots of full application broken reloads when developing.
This moves all of DiscourseAI into a Zeitwerk compatible structure.
It also leaves some minimal amount of manual loading (automation - which is loading into an existing namespace that may or may not be there)
To avoid needing /lib/discourse_ai/... we mount a namespace thus we are able to keep /lib pointed at ::DiscourseAi
Various files were renamed to get around zeitwerk rules and minimize usage of custom inflections
Though we can get custom inflections to work it is not worth it, will require a Discourse core patch which means we create a hard dependency.
Penar Musaraj
Roman Rizzi
Sam
Jarek Radosz
Rafael dos Santos Silva