Go to file
Sam 5e80f93e4c
FEATURE: PDF support for rag pipeline (#1118)
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`
2025-02-14 12:15:07 +11:00
.github/workflows Initial commit 2023-02-17 11:33:47 -03:00
admin/assets/javascripts/discourse FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
app FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
assets FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
config FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
db FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
discourse_automation FEATURE: Select stop sequences from triage script (#1010) 2024-12-06 11:13:47 -03:00
evals FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
lib FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
public/ai-share UX: improve artifact styling add direct share link (#930) 2024-11-20 13:13:03 +11:00
spec FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
svg-icons UX: improve embeddings config styles (#1085) 2025-01-24 16:24:59 +11:00
test/javascripts FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
tokenizers FEATURE: Gemini Tokenizer (#1088) 2025-01-23 18:20:35 -03:00
.discourse-compatibility DEV: Pin version for Discourse <3.5.0.beta1-dev (#1114) 2025-02-05 19:57:52 +01:00
.gitignore FEATURE: PDF support for rag pipeline (#1118) 2025-02-14 12:15:07 +11:00
.npmrc DEV: Switch to use pnpm (#833) 2024-10-14 13:37:20 +02:00
.prettierignore FEATURE: UI to update ai personas on admin page (#290) 2023-11-21 16:56:43 +11:00
.prettierrc.cjs DEV: Update linting configs (#280) 2023-11-03 11:30:09 +00:00
.rubocop.yml DEV: Expose AI spam scanning metrics (#1077) 2025-01-27 11:57:01 +08:00
.streerc DEV: Update linting configs (#280) 2023-11-03 11:30:09 +00:00
.template-lintrc.cjs DEV: Update linting (#326) 2023-11-29 23:01:48 +01:00
Gemfile DEV: Update linting configs (#280) 2023-11-03 11:30:09 +00:00
Gemfile.lock Build(deps-dev): Bump rack from 3.1.6 to 3.1.10 (#1124) 2025-02-13 12:09:04 +11:00
LICENSE Initial commit 2023-02-17 11:33:47 -03:00
README.md CHORE: Update Readme (#185) 2023-09-04 15:46:35 -03:00
about.json DEV: Expose AI spam scanning metrics (#1077) 2025-01-27 11:57:01 +08:00
eslint.config.mjs DEV: Update eslint config (#917) 2024-11-19 11:57:40 +01:00
package.json DEV: Bump dependencies and fix linting (#1115) 2025-02-06 17:42:32 +01:00
plugin.rb DEV: Expose AI spam scanning metrics (#1077) 2025-01-27 11:57:01 +08:00
pnpm-lock.yaml DEV: Bump dependencies and fix linting (#1115) 2025-02-06 17:42:32 +01:00
translator.yml UX: Display the indexing progress for RAG uploads (#557) 2024-04-09 11:03:07 -03:00

README.md

Discourse AI Plugin

Plugin Summary

For more information, please see: https://meta.discourse.org/t/discourse-ai/259214?u=falco