Commit Graph

233 Commits

Author SHA1 Message Date
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 a1c649965f
FEATURE: Auto image captions (#637) 2024-05-27 10:49:24 -07:00
Ted Johansson d8a0f44fed
FIX: Amend incorrect translation keys (#639)
I am enabling config.i18n.raise_on_missing_translations in core. This revealed a couple of broken translations in the plugin.
2024-05-24 20:00:36 +08:00
Sam d5c23f01ff
FIX: correct gemini streaming implementation (#632)
This also implements image support and gemini-flash support
2024-05-22 16:35:29 +10:00
Roman Rizzi 3a9080dd14
FEATURE: Test LLM configuration (#634) 2024-05-21 13:35:50 -03:00
Discourse Translator Bot 2b473dd4a5
Update translations (#633) 2024-05-21 17:41:00 +02:00
Sam 232f12eba6
FEATURE: JavaScript evaluation tool (#630)
This is similar to code interpreter by ChatGPT, except that it uses
JavaScript as the execution engine.

Safeguards were added to ensure memory is constrained and evaluation
times out.
2024-05-21 07:57:01 +10:00
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
Sam 255139056d
FEATURE: safeguard to avoid over triage (#626)
- a post can be triaged a maximum of twice a minute
- system can run a total of 60 triages a minute

Low defaults were picked to safeguard against any possible loops

This can be amended if required via hidden site settings.
2024-05-16 16:49:44 +10:00
Sam 3db89bfdc8
FIX: incorrect description for LLM field (#623) 2024-05-14 16:55:25 -07:00
Discourse Translator Bot 28647b81fe
Update translations (#620) 2024-05-14 16:19:53 +02:00
Sam 8eee6893d6
FEATURE: GPT4o support and better auditing (#618)
- 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
2024-05-14 13:28:46 +10:00
Roman Rizzi e22194f321
HACK: Llama3 support for summarization/AI helper. (#616)
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.
2024-05-13 15:54:42 -03:00
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
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
Discourse Translator Bot 27827c0898
Update translations (#605) 2024-05-07 09:33:25 -04:00
Roman Rizzi 4f1a3effe0
REFACTOR: Migrate Vllm/TGI-served models to the OpenAI format. (#588)
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..
2024-05-07 10:02:16 -03:00
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
Discourse Translator Bot aab59b9327
Update translations (#598) 2024-04-30 21:57:37 +02:00
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
Discourse Translator Bot 66804bc13c
Update translations (#587) 2024-04-23 16:22:37 +02:00
Sam bd6f5caeac
FEATURE: Stable diffusion 3 support (#582)
- Adds support for sd3 and sd3 turbo models - this requires new endpoints
- Adds a hack to normalize arrays in the tool calls
- Removes some leftover code
- Adds support for aspect ratio as well so you can generate wide or tall images
2024-04-19 18:08:16 +10:00
Sam 50be66ee63
FEATURE: Gemini 1.5 pro support and Claude Opus bedrock support (#580)
- Updated AI Bot to only support Gemini 1.5 (used to support 1.0) - 1.0 was removed cause it is not appropriate for Bot usage
- Summaries and automation can now lean on Gemini 1.5 pro
- Amazon added support for Claude 3 Opus, added internal support for it on bedrock
2024-04-17 15:37:19 +10:00
Discourse Translator Bot c2b2741f3d
Update translations (#579) 2024-04-16 17:38:00 +02:00
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
Sam b906046aad
FEATURE: Add Cohere models to AI helper and automation (#576) 2024-04-12 14:46:58 +10:00
Rafael dos Santos Silva 253e0b7b39
FEATURE: Mixtral/Mistral/Haiku Automation Support (#571)
Adds new models to automation, and makes LLM output parsing more robust.
2024-04-11 09:50:46 -03:00
Sam 7f16d3ad43
FEATURE: Cohere Command R support (#558)
- 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.
2024-04-11 07:24:17 +10:00
Rafael dos Santos Silva eb93b21769
FEATURE: Add BGE-M3 embeddings support (#569)
BAAI/bge-m3 is an interesting model, that is multilingual and with a
context size of 8192. Even with a 16x larger context, it's only 4x slower
to compute it's embeddings on the worst case scenario.

Also includes a minor refactor of the rake task, including setting model
and concurrency levels when running the backfill task.
2024-04-10 17:24:01 -03:00
Discourse Translator Bot 310238d38a
Update translations (#566) 2024-04-09 18:48:54 +02:00
Roman Rizzi aa8918911d
UX: Display the indexing progress for RAG uploads (#557) 2024-04-09 11:03:07 -03:00
Rafael dos Santos Silva 969fbae21e
DEV: Hide quick search setting since it's experimental (#559) 2024-04-05 12:12:37 -03:00
Sam 6f5f34184b
FEATURE: add Claude 3 Haiku bot support (#552)
it is close in performance to GPT 4 at a fraction of the cost,
nice to add it to the mix.

Also improves a test case to simulate streaming, I am hunting for
the "calls" word that is jumping into function calls and can't quite
find it.
2024-04-03 16:06:27 +11:00
Discourse Translator Bot 08b53e851c
Update translations (#551) 2024-04-02 18:19:55 +02:00
Roman Rizzi 1f1c94e5c6
FEATURE: AI Bot RAG support. (#537)
This PR lets you associate uploads to an AI persona, which we'll split and generate embeddings from. When building the system prompt to get a bot reply, we'll do a similarity search followed by a re-ranking (if available). This will let us find the most relevant fragments from the body of knowledge you associated with the persona, resulting in better, more informed responses.

For now, we'll only allow plain-text files, but this will change in the future.

Commits:

* FEATURE: RAG embeddings for the AI Bot

This first commit introduces a UI where admins can upload text files, which we'll store, split into fragments,
and generate embeddings of. In a next commit, we'll use those to give the bot additional information during
conversations.

* Basic asymmetric similarity search to provide guidance in system prompt

* Fix tests and lint

* Apply reranker to fragments

* Uploads filter, css adjustments and file validations

* Add placeholder for rag fragments

* Update annotations
2024-04-01 13:43:34 -03:00
Sam fb81307c59
FEATURE: web browsing tool (#548)
This pull request makes several improvements and additions to the GitHub-related tools and personas in the `discourse-ai` repository:

1. It adds the `WebBrowser` tool to the  `Researcher` persona, allowing the AI to visit web pages, retrieve HTML content, extract the main content, and convert it to plain text.

2. It updates the `GithubFileContent`, `GithubPullRequestDiff`, and `GithubSearchCode` tools to handle HTTP responses more robustly (introducing size limits). 

3. It refactors the `send_http_request` method in the `Tool` class to follow redirects when specified, and to read the response body in chunks to avoid memory issues with large responses. (only for WebBrowser)

4. It updates the system prompt for the `Researcher` persona to provide more detailed guidance on when to use Google search vs web browsing, and how to optimize tool usage and reduce redundant requests.

5. It adds a new `web_browser_spec.rb` file with tests for the `WebBrowser` tool, covering various scenarios like handling different HTML structures and following redirects.
2024-03-28 16:01:58 +11:00
Sam 61e4c56e1a
FEATURE: Add vision support to AI personas (Claude 3) (#546)
This commit adds the ability to enable vision for AI personas, allowing them to understand images that are posted in the conversation.

For personas with vision enabled, any images the user has posted will be resized to be within the configured max_pixels limit, base64 encoded and included in the prompt sent to the AI provider.

The persona editor allows enabling/disabling vision and has a dropdown to select the max supported image size (low, medium, high). Vision is disabled by default.

This initial vision support has been tested and implemented with Anthropic's claude-3 models which accept images in a special format as part of the prompt.

Other integrations will need to be updated to support images.

Several specs were added to test the new functionality at the persona, prompt building and API layers.

 - Gemini is omitted, pending API support for Gemini 1.5. Current Gemini bot is not performing well, adding images is unlikely to make it perform any better.

 - Open AI is omitted, vision support on GPT-4 it limited in that the API has no tool support when images are enabled so we would need to full back to a different prompting technique, something that would add lots of complexity


---------

Co-authored-by: Martin Brennan <martin@discourse.org>
2024-03-27 14:30:11 +11:00
Discourse Translator Bot 82387cc51d
Update translations (#547) 2024-03-26 10:21:23 -03:00
Martin Brennan fb0d56324f
FEATURE: Improve admin plugin UI and use new plugins show route (#512)
This commit changes Discourse AI's admin plugin page to use the new plugin
show route. The UI for persona editing has also been improved for consistency,
and other plugin UIs will follow suit:

Settings for the plugin are now listed in the plugin UI and can be changed
from there directly after core PR discourse/discourse#26154 is merged.

See also:

* https://github.com/discourse/discourse/pull/26024
* https://github.com/discourse/discourse/pull/26154
* https://github.com/discourse/discourse/pull/26254
2024-03-21 14:29:56 +10:00
Discourse Translator Bot 1a55d7f6e7
Update translations (#536) 2024-03-19 16:00:17 +01:00
Sam d7ed8180af
FEATURE: allow suppression of notifications from report generation (#533)
* FEATURE: allow suppression of notifications from report generation

Previously we needed to do this by hand, unfortunately this uses up
too many tokens and is very hard to discover.

New option means that we can trivially disable notifications without
needing any prompt engineering.

* URI.parse is safer, use it
2024-03-16 08:05:03 +11:00
David Taylor dfc13fc631
UX: Add title suffix to shared AI pages (#531) 2024-03-15 10:31:58 +00:00
Rafael dos Santos Silva 3b8f900486
FIX: Handle unicode on tokenizer (#515)
* FIX: Handle unicode on tokenizer

Our fast track code broke when strings had characters who are longer in tokens than
in UTF-8.

Admins can set `DISCOURSE_AI_STRICT_TOKEN_COUNTING: true` in app.yml to ensure token counting is strict, even if slower.


Co-authored-by: wozulong <sidle.pax_0e@icloud.com>
2024-03-14 17:33:30 -03:00
Sam ea5c38686e
FIX: expire assets when CSS changes FIX: missing translation on share page (#528)
* FIX: expire assets when CSS changes
FIX: missing translation on share page

Also add trivial image styling

* oops not needed
2024-03-13 20:52:33 +11:00
Discourse Translator Bot 25d283b527
Update translations (#524) 2024-03-12 15:40:21 +01:00