Discource-C
/
discourse-ai
mirror of https://github.com/discourse/discourse-ai.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
discourse-ai/config/locales/client.en.yml

318 lines
14 KiB
YAML
Raw Normal View History

Initial commit
2023-02-17 09:33:47 -05:00
en:
DEV: Categorize plugin settings into discourse_ai (#144) Moving the plugin settings into a more specific category makes them easier to find in the plugin UI and removes them from the generic "Plugins" tab.
2023-08-21 13:46:34 -04:00
admin_js:
admin:
site_settings:
categories:
discourse_ai: "Discourse AI"
Initial commit
2023-02-17 09:33:47 -05:00
js:
FEATURE: automation rule for triaging posts using LLM (#236) The new automation rule can be used to perform llm based classification and categorization of topics. You specify a system prompt (which has %%POST%% as an input), if it returns a particular piece of text then we will apply rules such as tagging, hiding, replying or categorizing. This can be used as a spam filter, a "oops you are in the wrong place" filter and so on. Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com>
2023-10-02 17:55:30 -04:00
discourse_automation:
FEATURE: LLM based peroidical summary report (#357) Introduce a Discourse Automation based periodical report. Depends on Discourse Automation. Report works best with very large context language models such as GPT-4-Turbo and Claude 2. - Introduces final_insts to generic llm format, for claude to work best it is better to guide the last assistant message (we should add this to other spots as well) - Adds GPT-4 turbo support to generic llm interface
2023-12-18 20:04:15 -05:00
ai_models:
gpt_4_turbo: GPT 4 Turbo
gpt_4: GPT 4
gpt_3_5_turbo: GPT 3.5 Turbo
claude_2: Claude 2
gemini_pro: Gemini Pro
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 01:37:19 -04:00
gemini_1_5_pro: Gemini 1.5 Pro
FEATURE: support for claude opus and sonnet (#508) 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
2024-03-05 14:04:37 -05:00
claude_3_opus: Claude 3 Opus
claude_3_sonnet: Claude 3 Sonnet
FEATURE: Mixtral/Mistral/Haiku Automation Support (#571) Adds new models to automation, and makes LLM output parsing more robust.
2024-04-11 08:50:46 -04:00
claude_3_haiku: Claude 3 Haiku
mixtral_8x7b_instruct_v0_1: Mixtral 8x7B Instruct V0.1
mistral_7b_instruct_v0_2: Mistral 7B Instruct V0.2
FEATURE: Add Cohere models to AI helper and automation (#576)
2024-04-12 00:46:58 -04:00
command_r: Cohere Command R
command_r_plus: Cohere Command R+
FEATURE: automation rule for triaging posts using LLM (#236) The new automation rule can be used to perform llm based classification and categorization of topics. You specify a system prompt (which has %%POST%% as an input), if it returns a particular piece of text then we will apply rules such as tagging, hiding, replying or categorizing. This can be used as a spam filter, a "oops you are in the wrong place" filter and so on. Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com>
2023-10-02 17:55:30 -04:00
scriptables:
FEATURE: LLM based peroidical summary report (#357) Introduce a Discourse Automation based periodical report. Depends on Discourse Automation. Report works best with very large context language models such as GPT-4-Turbo and Claude 2. - Introduces final_insts to generic llm format, for claude to work best it is better to guide the last assistant message (we should add this to other spots as well) - Adds GPT-4 turbo support to generic llm interface
2023-12-18 20:04:15 -05:00
llm_report:
fields:
sender:
label: "Sender"
description: "The user that will send the report"
receivers:
label: "Receivers"
FEATURE: allow sending AI based report to a topic (#377) This makes the reporting far more flexible cause it can target a far wider audience by pointing it at a topic in a secure category or an existing PM
2023-12-21 19:46:23 -05:00
description: "The users that will receive the report (emails will be sent direct emails, usernames will be sent a PM)"
topic_id:
label: "Topic ID"
description: "The topic id to post the report to"
FEATURE: LLM based peroidical summary report (#357) Introduce a Discourse Automation based periodical report. Depends on Discourse Automation. Report works best with very large context language models such as GPT-4-Turbo and Claude 2. - Introduces final_insts to generic llm format, for claude to work best it is better to guide the last assistant message (we should add this to other spots as well) - Adds GPT-4 turbo support to generic llm interface
2023-12-18 20:04:15 -05:00
title:
label: "Title"
description: "The title of the report"
days:
label: "Days"
description: "The timespan of the report"
offset:
label: "Offset"
description: "When testing you may want to run the report historically, use offset to start the report in an earlier date"
instructions:
label: "Instructions"
description: "The instructions provided to the large language model"
sample_size:
label: "Sample Size"
description: "The number of posts to sample for the report"
tokens_per_post:
label: "Tokens per post"
description: "The number of llm tokens to use per post"
model:
label: "Model"
description: "LLM to use for report generation"
categories:
label: "Categories"
FIX: typo (#432)
2024-01-18 10:38:29 -05:00
description: "Filter topics only to these categories"
FEATURE: LLM based peroidical summary report (#357) Introduce a Discourse Automation based periodical report. Depends on Discourse Automation. Report works best with very large context language models such as GPT-4-Turbo and Claude 2. - Introduces final_insts to generic llm format, for claude to work best it is better to guide the last assistant message (we should add this to other spots as well) - Adds GPT-4 turbo support to generic llm interface
2023-12-18 20:04:15 -05:00
tags:
label: "Tags"
description: "Filter topics only to these tags"
FEATURE: allow excluding tags and categories from LLM report (#447) Also - Better diagnostics, output model being used - Prompt LLM that true content is being injected in <context> tag
2024-01-29 23:55:05 -05:00
exclude_tags:
label: "Exclude Tags"
description: "Exclude topics with these tags"
exclude_categories:
label: "Exclude Categories"
description: "Exclude topics with these categories"
FEATURE: LLM based peroidical summary report (#357) Introduce a Discourse Automation based periodical report. Depends on Discourse Automation. Report works best with very large context language models such as GPT-4-Turbo and Claude 2. - Introduces final_insts to generic llm format, for claude to work best it is better to guide the last assistant message (we should add this to other spots as well) - Adds GPT-4 turbo support to generic llm interface
2023-12-18 20:04:15 -05:00
allow_secure_categories:
label: "Allow secure categories"
description: "Allow the report to be generated for topics in secure categories"
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
2024-03-15 17:05:03 -04:00
suppress_notifications:
label: "Suppress Notifications"
description: "Suppress notifications the report may generate by transforming to content. This will remap mentions and internal links."
FEATURE: LLM based peroidical summary report (#357) Introduce a Discourse Automation based periodical report. Depends on Discourse Automation. Report works best with very large context language models such as GPT-4-Turbo and Claude 2. - Introduces final_insts to generic llm format, for claude to work best it is better to guide the last assistant message (we should add this to other spots as well) - Adds GPT-4 turbo support to generic llm interface
2023-12-18 20:04:15 -05:00
debug_mode:
label: "Debug Mode"
description: "Enable debug mode to see the raw input and output of the LLM"
priority_group:
label: "Priority Group"
FEATURE: even smoother streaming (#420) Account properly for function calls, don't stream through <details> blocks - Rush cooked content back to client - Wait longer (up to 60 seconds) before giving up on streaming - Clean up message bus channels so we don't have leftover data - Make ai streamer much more reusable and much easier to read - If buffer grows quickly, rush update so you are not artificially waiting - Refine prompt interface - Fix lost system message when prompt gets long
2024-01-15 02:51:14 -05:00
description: "Prioritize content from this group in the report"
FEATURE: fine tune llm report to follow instructions more closely (#451) - Allow users to supply top_p and temperature values, which means people can fine tune randomness - Fix bad localization string - Fix bad remapping of max tokens in gemini - Add support for top_p as a general param to llms - Amend system prompt so persona stops treating a user as an adversary
2024-01-30 17:58:25 -05:00
temperature:
label: "Temperature"
description: "Temperature to use for the LLM, increase to increase randomness (0 to use model default)"
top_p:
label: "Top P"
description: "Top P to use for the LLM, increase to increase randomness (0 to use model default)"
FEATURE: LLM based peroidical summary report (#357) Introduce a Discourse Automation based periodical report. Depends on Discourse Automation. Report works best with very large context language models such as GPT-4-Turbo and Claude 2. - Introduces final_insts to generic llm format, for claude to work best it is better to guide the last assistant message (we should add this to other spots as well) - Adds GPT-4 turbo support to generic llm interface
2023-12-18 20:04:15 -05:00
FEATURE: automation rule for triaging posts using LLM (#236) The new automation rule can be used to perform llm based classification and categorization of topics. You specify a system prompt (which has %%POST%% as an input), if it returns a particular piece of text then we will apply rules such as tagging, hiding, replying or categorizing. This can be used as a spam filter, a "oops you are in the wrong place" filter and so on. Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com>
2023-10-02 17:55:30 -04:00
llm_triage:
fields:
system_prompt:
label: "System Prompt"
description: "The prompt that will be used to triage, be sure for it to reply with a single word you can use to trigger the action"
search_for_text:
label: "Search for text"
description: "If the following text appears in the llm reply, apply this actions"
category:
label: "Category"
description: "Category to apply to the topic"
tags:
label: "Tags"
description: "Tags to apply to the topic"
canned_reply:
label: "Reply"
description: "Raw text of canned reply to post on the topic"
canned_reply_user:
label: "Reply User"
description: "Username of the user to post the canned reply"
hide_topic:
label: "Hide topic"
description: "Make topic non visible to the public if triggered"
FEATURE: Option for AI triage to send a post to the review queue (#498) Option for AI triage to send a post to the review queue
2024-02-28 20:33:28 -05:00
flag_post:
label: "Send to review"
description: "Puts the post into the review queue if triggered, for moderators to triage"
FEATURE: automation rule for triaging posts using LLM (#236) The new automation rule can be used to perform llm based classification and categorization of topics. You specify a system prompt (which has %%POST%% as an input), if it returns a particular piece of text then we will apply rules such as tagging, hiding, replying or categorizing. This can be used as a spam filter, a "oops you are in the wrong place" filter and so on. Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com>
2023-10-02 17:55:30 -04:00
model:
label: "Model"
description: "Either gpt-4 or gpt-3-5-turbo or claude-2"
FEATURE: Composer AI helper (#8) * FEATURE: Composer AI helper This change introduces a new composer button for the group members listed in the `ai_helper_allowed_groups` site setting. Users can use chatGPT to review, improve, or translate their posts to English. * Add a safeguard for PMs and don't rely on parentView
2023-03-15 16:02:20 -04:00
discourse_ai:
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
title: "AI"
FEATURE: Chat channel summarization. (#32) * start summary module * chat channel summarization * FEATURE: modal for channel summarization --------- Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2023-04-04 10:24:09 -04:00
modals:
select_option: "Select an option..."
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
ai_persona:
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 00:29:56 -04:00
back: Back
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
name: Name
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 00:29:56 -04:00
edit: Edit
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
description: Description
FEATURE: mentionable personas and random picker tool, context limits (#466) 1. Personas are now optionally mentionable, meaning that you can mention them either from public topics or PMs - Mentioning from PMs helps "switch" persona mid conversation, meaning if you want to look up sites setting you can invoke the site setting bot, or if you want to generate an image you can invoke dall e - Mentioning outside of PMs allows you to inject a bot reply in a topic trivially - We also add the support for max_context_posts this allow you to limit the amount of context you feed in, which can help control costs 2. Add support for a "random picker" tool that can be used to pick random numbers 3. Clean up routing ai_personas -> ai-personas 4. Add Max Context Posts so users can control how much history a persona can consume (this is important for mentionable personas) Co-authored-by: Martin Brennan <martin@discourse.org>
2024-02-15 00:37:59 -05:00
no_llm_selected: "No language model selected"
max_context_posts: "Max Context Posts"
max_context_posts_help: "The maximum number of posts to use as context for the AI when responding to a user. (empty for default)"
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>
2024-03-26 23:30:11 -04:00
vision_enabled: Vision Enabled
vision_enabled_help: If enabled, the AI will attempt to understand images users post in the topic, depends on the model being used supporting vision. Anthropic Claude 3 models support vision.
vision_max_pixels: Supported image size
vision_max_pixel_sizes:
low: Low Quality - cheapest (256x256)
medium: Medium Quality (512x512)
high: High Quality - slowest (1024x1024)
FEATURE: mentionable personas and random picker tool, context limits (#466) 1. Personas are now optionally mentionable, meaning that you can mention them either from public topics or PMs - Mentioning from PMs helps "switch" persona mid conversation, meaning if you want to look up sites setting you can invoke the site setting bot, or if you want to generate an image you can invoke dall e - Mentioning outside of PMs allows you to inject a bot reply in a topic trivially - We also add the support for max_context_posts this allow you to limit the amount of context you feed in, which can help control costs 2. Add support for a "random picker" tool that can be used to pick random numbers 3. Clean up routing ai_personas -> ai-personas 4. Add Max Context Posts so users can control how much history a persona can consume (this is important for mentionable personas) Co-authored-by: Martin Brennan <martin@discourse.org>
2024-02-15 00:37:59 -05:00
mentionable: Mentionable
mentionable_help: If enabled, users in allowed groups can mention this user in posts and messages, the AI will respond as this persona.
user: User
work in progress adding roles to personas # Conflicts: # app/models/ai_persona.rb
2024-05-01 01:39:13 -04:00
role: Role
role_options:
bot: Bot
message_responder: Message Responder
FEATURE: mentionable personas and random picker tool, context limits (#466) 1. Personas are now optionally mentionable, meaning that you can mention them either from public topics or PMs - Mentioning from PMs helps "switch" persona mid conversation, meaning if you want to look up sites setting you can invoke the site setting bot, or if you want to generate an image you can invoke dall e - Mentioning outside of PMs allows you to inject a bot reply in a topic trivially - We also add the support for max_context_posts this allow you to limit the amount of context you feed in, which can help control costs 2. Add support for a "random picker" tool that can be used to pick random numbers 3. Clean up routing ai_personas -> ai-personas 4. Add Max Context Posts so users can control how much history a persona can consume (this is important for mentionable personas) Co-authored-by: Martin Brennan <martin@discourse.org>
2024-02-15 00:37:59 -05:00
create_user: Create User
create_user_help: You can optionally attach a user to this persona. If you do, the AI will use this user to respond to requests.
default_llm: Default Language Model
default_llm_help: The default language model to use for this persona. Required if you wish to mention persona on public posts.
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.
2024-04-29 23:49:21 -04:00
question_consolidator_llm: Language Model for Question Consolidator
question_consolidator_llm_help: The language model to use for the question consolidator, you may choose a less powerful model to save costs.
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
system_prompt: System Prompt
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.
2024-04-29 23:49:21 -04:00
show_indexing_options: "Show Upload Options"
hide_indexing_options: "Hide Upload Options"
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
save: Save
saved: AI Persona Saved
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 00:29:56 -04:00
enabled: "Enabled?"
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
commands: Enabled Commands
allowed_groups: Allowed Groups
confirm_delete: Are you sure you want to delete this persona?
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 00:29:56 -04:00
new: "New Persona"
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
title: "AI Personas"
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 00:29:56 -04:00
short_title: "Personas"
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
delete: Delete
FEATURE: allow personas to supply top_p and temperature params (#459) * FEATURE: allow personas to supply top_p and temperature params Code assistance generally are more focused at a lower temperature This amends it so SQL Helper runs at 0.2 temperature vs the more common default across LLMs of 1.0. Reduced temperature leads to more focused, concise and predictable answers for the SQL Helper * fix tests * This is not perfect, but far better than what we do today Instead of fishing for 1. Draft sequence 2. Draft body We skip (2), this means the composer "only" needs 1 http request to open, we also want to eliminate (1) but it is a bit of a trickier core change, may figure out how to pull it off (defer it to first draft save) Value of bot drafts < value of opening bot conversations really fast
2024-02-02 15:09:34 -05:00
temperature: Temperature
temperature_help: Temperature to use for the LLM, increase to increase creativity (leave empty to use model default, generally a value from 0.0 to 2.0)
top_p: Top P
top_p_help: Top P to use for the LLM, increase to increase randomness (leave empty to use model default, generally a value from 0.0 to 1.0)
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
priority: Priority
priority_help: Priority personas are displayed to users at the top of the persona list. If multiple personas have priority, they will be sorted alphabetically.
FEATURE: allow personas to provide command options (#331) Personas now support providing options for commands. This PR introduces a single option "base_query" for the SearchCommand. When supplied all searches the persona will perform will also include the pre-supplied filter. This can allow personas to search a subset of the forum (such as documentation) This system is extensible we can add options to any command trivially.
2023-12-07 16:42:56 -05:00
command_options: "Command Options"
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 09:22:06 -04:00
rag_chunk_tokens: "Upload Chunk Tokens"
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 09:32:46 -04:00
rag_chunk_tokens_help: "The number of tokens to use for each chunk in the RAG model. Increase to increase the amount of context the AI can use. (changing will re-index all uploads)"
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 09:22:06 -04:00
rag_chunk_overlap_tokens: "Upload Chunk Overlap Tokens"
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 09:32:46 -04:00
rag_chunk_overlap_tokens_help: "The number of tokens to overlap between chunks in the RAG model. (changing will re-index all uploads)"
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 09:22:06 -04:00
rag_conversation_chunks: "Search Conversation Chunks"
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 09:32:46 -04:00
rag_conversation_chunks_help: "The number of chunks to use for the RAG model searches. Increase to increase the amount of context the AI can use."
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 00:29:56 -04:00
what_are_personas: "What are AI Personas?"
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
no_persona_selected: |
AI Personas are a powerful feature that allows you to customize the behavior of the AI engine in your Discourse forum. They act as a 'system message' that guides the AI's responses and interactions, helping to create a more personalized and engaging user experience.
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 00:29:56 -04:00
#### Why use AI Personas?
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
With AI Personas, you can tailor the AI's behavior to better fit the context and tone of your forum. Whether you want the AI to be more formal for a professional setting, more casual for a community forum, or even embody a specific character for a role-playing game, AI Personas give you the flexibility to do so.
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 00:29:56 -04:00
#### Group-Specific Access to AI Personas
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
Moreover, you can set it up so that certain user groups have access to specific personas. This means you can have different AI behaviors for different sections of your forum, further enhancing the diversity and richness of your community's interactions.
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 01:06:27 -04:00
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 12:43:34 -04:00
uploads:
title: "Uploads"
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.
2024-04-29 23:49:21 -04:00
description: "Your AI persona will be able to search and reference the content of included files. Uploaded files should be formatted as plaintext (.txt) or markdown (.md)."
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 12:43:34 -04:00
button: "Add Files"
filter: "Filter uploads"
UX: Display the indexing progress for RAG uploads (#557)
2024-04-09 10:03:07 -04:00
indexed: "Indexed"
indexing: "Indexing"
uploaded: "Ready to be indexed"
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 09:22:06 -04:00
uploading: "Uploading..."
remove: "Remove upload"
FEATURE: UI to update ai personas on admin page (#290) Introduces a UI to manage customizable personas (admin only feature) Part of the change was some extensive internal refactoring: - AIBot now has a persona set in the constructor, once set it never changes - Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly - Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work - Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure - name uniqueness, and only allow certain properties to be touched for system personas. - (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona. - (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta - This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis - Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length - Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things - Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up. - Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer - Migrates the persona selector to gjs --------- Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com> Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 00:56:43 -05:00
FEATURE: attempt to include related topics above suggested (#28) Allows related topics to show up for logged on users - Introduces a new "Related Topics" block above suggested when related topics exist - Renames `ai_embeddings_semantic_suggested_topics_anons_enabled` -> `ai_embeddings_semantic_suggested_topics_enabled` (given it is only deployed on 1 site not bothering with a migration) - Adds an integration test to ensure data arrives correctly on the client
2023-03-30 18:07:22 -04:00
related_topics:
FIX: Use "Related Topics" label consistently (#221)
2023-09-12 15:23:24 -04:00
title: "Related Topics"
UX: Update related-topics to follow <MoreTopics/> conventions (#118)
2023-07-31 17:33:37 -04:00
pill: "Related"
FEATURE: Composer AI helper (#8) * FEATURE: Composer AI helper This change introduces a new composer button for the group members listed in the `ai_helper_allowed_groups` site setting. Users can use chatGPT to review, improve, or translate their posts to English. * Add a safeguard for PMs and don't rely on parentView
2023-03-15 16:02:20 -04:00
ai_helper:
title: "Suggest changes using AI"
description: "Choose one of the options below, and the AI will suggest you a new version of the text."
selection_hint: "Hint: You can also select a portion of the text before opening the helper to rewrite only that."
FEATURE: Additional AI suggestion options (#176)
2023-09-01 20:10:58 -04:00
suggest: "Suggest with AI"
FIX: Show warning when trying to generate suggestions without content (#175)
2023-08-29 14:58:45 -04:00
missing_content: "Please enter some content to generate suggestions."
FEATURE: AI Helper Context Menu (#148)
2023-08-23 13:35:40 -04:00
context_menu:
FEATURE: Create custom prompts with composer AI helper (#214) * DEV: Add icon support * DEV: Add basic setup for custom prompt menu * FEATURE: custom prompt backend * fix custom prompt param check * fix custom prompt replace * WIP * fix custom prompt usage * fixes * DEV: Update front-end * DEV: No more custom prompt state * DEV: Add specs * FIX: Title/Category/Tag suggestions Suggestion dropdowns broke because it `messages_with_user_input(user_input)` expects a hash now. * DEV: Apply syntax tree * DEV: Restrict custom prompts to configured groups * oops * fix tests * lint * I love tests * lint is cool tho --------- Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
2023-09-25 14:12:54 -04:00
back: "Back"
FEATURE: AI Helper Context Menu (#148)
2023-08-23 13:35:40 -04:00
trigger: "AI"
undo: "Undo"
loading: "AI is generating"
cancel: "Cancel"
regen: "Try Again"
DEV: Add review menu state (#159)
2023-08-24 20:49:24 -04:00
view_changes: "View Changes"
confirm: "Confirm"
revert: "Revert"
changes: "Changes"
FEATURE: Create custom prompts with composer AI helper (#214) * DEV: Add icon support * DEV: Add basic setup for custom prompt menu * FEATURE: custom prompt backend * fix custom prompt param check * fix custom prompt replace * WIP * fix custom prompt usage * fixes * DEV: Update front-end * DEV: No more custom prompt state * DEV: Add specs * FIX: Title/Category/Tag suggestions Suggestion dropdowns broke because it `messages_with_user_input(user_input)` expects a hash now. * DEV: Apply syntax tree * DEV: Restrict custom prompts to configured groups * oops * fix tests * lint * I love tests * lint is cool tho --------- Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
2023-09-25 14:12:54 -04:00
custom_prompt:
title: "Custom Prompt"
placeholder: "Enter a custom prompt..."
submit: "Send Prompt"
FEATURE: AI helper on posts (#244) Adds an AI Helper function when selecting text while viewing a topic. --------- Co-authored-by: Keegan George <kgeorge13@gmail.com> Co-authored-by: Roman Rizzi <roman@discourse.org>
2023-10-23 10:41:36 -04:00
post_options_menu:
trigger: "Ask AI"
UX: Add title to button (#334)
2023-12-05 15:33:10 -05:00
title: "Ask AI"
FEATURE: AI helper on posts (#244) Adds an AI Helper function when selecting text while viewing a topic. --------- Co-authored-by: Keegan George <kgeorge13@gmail.com> Co-authored-by: Roman Rizzi <roman@discourse.org>
2023-10-23 10:41:36 -04:00
loading: "AI is generating"
close: "Close"
UX: Add copy button to generated suggestion (#296)
2023-11-17 12:25:41 -05:00
copy: "Copy"
copied: "Copied!"
FEATURE: Add streaming to post AI helper's explain option (#344) Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com> Co-authored-by: Roman Rizzi <roman@discourse.org>
2023-12-12 12:28:39 -05:00
cancel: "Cancel"
FEATURE: Proofread with post AI helper (#359)
2023-12-14 22:30:52 -05:00
fast_edit:
suggest_button: "Suggest Edit"
FEATURE: Generate post illustrations (#367)
2023-12-19 14:17:34 -05:00
thumbnail_suggestions:
title: "Suggested Thumbnails"
select: "Select"
selected: "Selected"
FEATURE: AI image caption (#470) This PR adds a new feature where you can generate captions for images in the composer using AI. --------- Co-authored-by: Rafael Silva <xfalcox@gmail.com>
2024-02-19 12:56:28 -05:00
image_caption:
button_label: "Caption with AI"
generating: "Generating caption..."
credits: "Captioned by AI"
save_caption: "Save"
FEATURE: Use dedicated reviewables for AI flags. (#4) This change adds two new reviewable types: ReviewableAIPost and ReviewableAIChatMessage. They have the same actions as their existing counterparts: ReviewableFlaggedPost and ReviewableChatMessage. We'll display the model used and their accuracy when showing these flags in the review queue and adjust the latter after staff performs an action, tracking a global accuracy per existing model in a separate table. * FEATURE: Dedicated reviewables for AI flags * Store and adjust model accuracy * Display accuracy in reviewable templates
2023-03-07 13:39:28 -05:00
reviewables:
model_used: "Model used:"
accuracy: "Accuracy:"
FEATURE: port to use claude-2 for chat bot (#114) Claude 1 costs the same and is less good than Claude 2. Make use of Claude 2 in all spots ... This also fixes streaming so it uses the far more efficient streaming protocol.
2023-07-26 21:24:44 -04:00
FEATURE: Semantic assymetric full-page search (#34) Depends on discourse/discourse#20915 Hooks to the full-page-search component using an experimental API and performs an assymetric similarity search using our embeddings database.
2023-03-31 14:29:56 -04:00
embeddings:
semantic_search: "Topics (Semantic)"
FEATURE: HyDE-powered semantic search. (#136) * FEATURE: HyDE-powered semantic search. It relies on the new outlet added on discourse/discourse#23390 to display semantic search results in an unobtrusive way. We'll use a HyDE-backed approach for semantic search, which consists on generating an hypothetical document from a given keywords, which gets transformed into a vector and used in a asymmetric similarity topic search. This PR also reorganizes the internals to have less moving parts, maintaining one hierarchy of DAOish classes for vector-related operations like transformations and querying. Completions and vectors created by HyDE will remain cached on Redis for now, but we could later use Postgres instead. * Missing translation and rate limiting --------- Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2023-09-05 10:08:23 -04:00
semantic_search_loading: "Searching for more results using AI"
DEV: Only allow semantic search on "Relevance" sort mode (#306)
2023-11-23 14:30:17 -05:00
semantic_search_disabled_sort: "AI Search disabled for this sort order, sort by Relevance to enable."
FEATURE: HyDE-powered semantic search. (#136) * FEATURE: HyDE-powered semantic search. It relies on the new outlet added on discourse/discourse#23390 to display semantic search results in an unobtrusive way. We'll use a HyDE-backed approach for semantic search, which consists on generating an hypothetical document from a given keywords, which gets transformed into a vector and used in a asymmetric similarity topic search. This PR also reorganizes the internals to have less moving parts, maintaining one hierarchy of DAOish classes for vector-related operations like transformations and querying. Completions and vectors created by HyDE will remain cached on Redis for now, but we could later use Postgres instead. * Missing translation and rate limiting --------- Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2023-09-05 10:08:23 -04:00
semantic_search_results:
DEV: Mix semantic search results with normal results (#278)
2023-11-17 15:46:59 -05:00
toggle: "Showing %{count} results found using AI"
toggle_hidden: "Hiding %{count} results found using AI"
FEATURE: HyDE-powered semantic search. (#136) * FEATURE: HyDE-powered semantic search. It relies on the new outlet added on discourse/discourse#23390 to display semantic search results in an unobtrusive way. We'll use a HyDE-backed approach for semantic search, which consists on generating an hypothetical document from a given keywords, which gets transformed into a vector and used in a asymmetric similarity topic search. This PR also reorganizes the internals to have less moving parts, maintaining one hierarchy of DAOish classes for vector-related operations like transformations and querying. Completions and vectors created by HyDE will remain cached on Redis for now, but we could later use Postgres instead. * Missing translation and rate limiting --------- Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2023-09-05 10:08:23 -04:00
none: "Sorry, our AI search found no matching topics."
FIX: Prevent no results label from showing when untrue (#384)
2023-12-27 19:42:13 -05:00
new: "Press 'Search' to begin looking for new results with AI"
A11Y: Add title attribute to sparkles icon for AI search results (#317)
2023-11-27 17:25:33 -05:00
ai_generated_result: "Search result found using AI"
FEATURE: AI Quick Semantic Search (#501) This PR adds AI semantic search to the search pop available on every page. It depends on several new and optional settings, like per post embeddings and a reranker model, so this is an experimental endeavour. --------- Co-authored-by: Rafael Silva <xfalcox@gmail.com>
2024-03-08 11:02:50 -05:00
quick_search:
suffix: "in all topics and posts with AI"
FEATURE: Chat channel summarization. (#32) * start summary module * chat channel summarization * FEATURE: modal for channel summarization --------- Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2023-04-04 10:24:09 -04:00
FEATURE: Introduce the ai-bot module (#52) This module lets you chat with our GPT bot inside a PM. The bot only replies to members of the groups listed on the ai_bot_allowed_groups setting and only if you invite it to participate in the PM.
2023-05-05 14:28:31 -04:00
ai_bot:
FEATURE: optional warning attached to all AI bot conversations (#137) * FEATURE: optional warning attached to all AI bot conversations This commit introduces `ai_bot_enable_chat_warning` which can be used to warn people prior to starting a chat with the bot. In particular this is useful if moderators are regularly reading chat transcripts as it sets expectations early. By default this is disabled. Also: - Stops making ajax call prior to opening composer - Hides PM title when starting a bot PM Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
2023-08-16 16:29:58 -04:00
pm_warning: "AI chatbot messages are monitored regularly by moderators."
UX: Add missing label translation (#64)
2023-05-16 15:56:30 -04:00
cancel_streaming: "Stop reply"
FEATURE: Less friction for starting a conversation with an AI bot. (#63) * FEATURE: Less friction for starting a conversation with an AI bot. This PR adds a new header icon as a shortcut to start a conversation with one of our AI Bots. After clicking and selecting one from the dropdown menu, we'll open the composer with some fields already filled (recipients and title). If you leave the title as is, we'll queue a job after five minutes to update it using a bot suggestion. * Update assets/javascripts/initializers/ai-bot-replies.js Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com> * Update assets/javascripts/initializers/ai-bot-replies.js Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com> --------- Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
2023-05-16 13:38:21 -04:00
default_pm_prefix: "[Untitled AI bot PM]"
UX: Add missing label translation (#64)
2023-05-16 15:56:30 -04:00
shortcut_title: "Start a PM with an AI bot"
FEATURE: allow easy sharing of bot conversations (#385) * FEATURE: allow easy sharing of bot conversations * Lean on new core API i * Added system spec for copy functionality * Update assets/javascripts/initializers/ai-bot-replies.js Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com> * discourse later insted of setTimeout * Update spec/system/ai_bot/share_spec.rb Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com> * feedback from review just check the whole payload * remove uneeded code * fix spec --------- Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com>
2023-12-29 03:47:47 -05:00
share: "Share AI conversation"
UX: copy change (#390)
2023-12-29 10:26:03 -05:00
conversation_shared: "Conversation copied"
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 09:22:06 -04:00
debug_ai: "View raw AI request and response"
debug_ai_modal:
title: "View AI interaction"
copy_request: "Copy request"
copy_response: "Copy response"
request_tokens: "Request tokens:"
response_tokens: "Response tokens:"
FEATURE: allow easy sharing of bot conversations (#385) * FEATURE: allow easy sharing of bot conversations * Lean on new core API i * Added system spec for copy functionality * Update assets/javascripts/initializers/ai-bot-replies.js Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com> * discourse later insted of setTimeout * Update spec/system/ai_bot/share_spec.rb Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com> * feedback from review just check the whole payload * remove uneeded code * fix spec --------- Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com>
2023-12-29 03:47:47 -05:00
FEATURE: Share conversations with AI via a URL (#521) This allows users to share a static page of an AI conversation with the rest of the world. By default this feature is disabled, it is enabled by turning on ai_bot_allow_public_sharing via site settings Precautions are taken when sharing 1. We make a carbonite copy 2. We minimize work generating page 3. We limit to 100 interactions 4. Many security checks - including disallowing if there is a mix of users in the PM. * Bonus commit, large PRs like this PR did not work with github tool large objects would destroy context Co-authored-by: Martin Brennan <martin@discourse.org>
2024-03-12 01:51:41 -04:00
share_full_topic_modal:
title: "Share Conversation Publicly"
share: "Share and Copy Link"
update: "Update and Copy Link"
delete: "Delete Share"
share_ai_conversation:
name: "Share AI Conversation"
title: "Share this AI conversation publicly"
FEATURE: allow easy sharing of bot conversations (#385) * FEATURE: allow easy sharing of bot conversations * Lean on new core API i * Added system spec for copy functionality * Update assets/javascripts/initializers/ai-bot-replies.js Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com> * discourse later insted of setTimeout * Update spec/system/ai_bot/share_spec.rb Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com> * feedback from review just check the whole payload * remove uneeded code * fix spec --------- Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com>
2023-12-29 03:47:47 -05:00
ai_label: "AI"
ai_title: "Conversation with AI"
share_modal:
FEATURE: Share conversations with AI via a URL (#521) This allows users to share a static page of an AI conversation with the rest of the world. By default this feature is disabled, it is enabled by turning on ai_bot_allow_public_sharing via site settings Precautions are taken when sharing 1. We make a carbonite copy 2. We minimize work generating page 3. We limit to 100 interactions 4. Many security checks - including disallowing if there is a mix of users in the PM. * Bonus commit, large PRs like this PR did not work with github tool large objects would destroy context Co-authored-by: Martin Brennan <martin@discourse.org>
2024-03-12 01:51:41 -04:00
title: "Copy AI conversation"
FEATURE: allow easy sharing of bot conversations (#385) * FEATURE: allow easy sharing of bot conversations * Lean on new core API i * Added system spec for copy functionality * Update assets/javascripts/initializers/ai-bot-replies.js Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com> * discourse later insted of setTimeout * Update spec/system/ai_bot/share_spec.rb Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com> * feedback from review just check the whole payload * remove uneeded code * fix spec --------- Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com>
2023-12-29 03:47:47 -05:00
copy: "Copy"
context: "Interactions to share:"
FEATURE: Share conversations with AI via a URL (#521) This allows users to share a static page of an AI conversation with the rest of the world. By default this feature is disabled, it is enabled by turning on ai_bot_allow_public_sharing via site settings Precautions are taken when sharing 1. We make a carbonite copy 2. We minimize work generating page 3. We limit to 100 interactions 4. Many security checks - including disallowing if there is a mix of users in the PM. * Bonus commit, large PRs like this PR did not work with github tool large objects would destroy context Co-authored-by: Martin Brennan <martin@discourse.org>
2024-03-12 01:51:41 -04:00
share_tip: Alternatively, you can share the entire conversation.
FEATURE: Introduce the ai-bot module (#52) This module lets you chat with our GPT bot inside a PM. The bot only replies to members of the groups listed on the ai_bot_allowed_groups setting and only if you invite it to participate in the PM.
2023-05-05 14:28:31 -04:00
UX: Improvements to the AI Bot header shortcut (#66) - Humanize model names - Focus composer editor when starting a PM with a bot - Correctly close the models dropdown when clicking outside
2023-05-17 14:59:48 -04:00
bot_names:
FEATURE: support for claude opus and sonnet (#508) 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
2024-03-05 14:04:37 -05:00
fake: "Fake Test Bot"
claude-3-opus: "Claude 3 Opus"
claude-3-sonnet: "Claude 3 Sonnet"
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 01:06:27 -04:00
claude-3-haiku: "Claude 3 Haiku"
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.
2024-04-10 17:24:17 -04:00
cohere-command-r-plus: "Cohere Command R Plus"
UX: Improvements to the AI Bot header shortcut (#66) - Humanize model names - Focus composer editor when starting a PM with a bot - Correctly close the models dropdown when clicking outside
2023-05-17 14:59:48 -04:00
gpt-4: "GPT-4"
FEATURE: implement GPT-4 turbo support (#345) Keep in mind: - GPT-4 is only going to be fully released next year - so this hardcodes preview model for now - Fixes streaming bugs which became a big problem with GPT-4 turbo - Adds Azure endpoing for turbo as well Co-authored-by: Martin Brennan <martin@discourse.org>
2023-12-10 22:59:57 -05:00
gpt-4-turbo: "GPT-4 Turbo"
UX: Improvements to the AI Bot header shortcut (#66) - Humanize model names - Focus composer editor when starting a PM with a bot - Correctly close the models dropdown when clicking outside
2023-05-17 14:59:48 -04:00
gpt-3:
5-turbo: "GPT-3.5"
FEATURE: port to use claude-2 for chat bot (#114) Claude 1 costs the same and is less good than Claude 2. Make use of Claude 2 in all spots ... This also fixes streaming so it uses the far more efficient streaming protocol.
2023-07-26 21:24:44 -04:00
claude-2: "Claude 2"
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 01:37:19 -04:00
gemini-1:
5-pro: "Gemini"
FEATURE: Add Mixtral support for AI Bot (#396)
2024-01-04 10:22:43 -05:00
mixtral-8x7B-Instruct-V0:
"1": "Mixtral-8x7B V0.1"
FEATURE: Expose sentiment classifications via the admin dashboard. (#284) This PR adds new reports for displaying information about post sentiments grouped by date and emotions group by TL. Depends on discourse/discourse#24274
2023-11-08 08:50:37 -05:00
sentiments:
dashboard:
title: "Sentiment"
FEATURE: Use dedicated reviewables for AI flags. (#4) This change adds two new reviewable types: ReviewableAIPost and ReviewableAIChatMessage. They have the same actions as their existing counterparts: ReviewableFlaggedPost and ReviewableChatMessage. We'll display the model used and their accuracy when showing these flags in the review queue and adjust the latter after staff performs an action, tracking a global accuracy per existing model in a separate table. * FEATURE: Dedicated reviewables for AI flags * Store and adjust model accuracy * Display accuracy in reviewable templates
2023-03-07 13:39:28 -05:00
review:
types:
FIX: Fix reviewable title translations (#18)
2023-03-20 09:09:20 -04:00
reviewable_ai_post:
FEATURE: Use dedicated reviewables for AI flags. (#4) This change adds two new reviewable types: ReviewableAIPost and ReviewableAIChatMessage. They have the same actions as their existing counterparts: ReviewableFlaggedPost and ReviewableChatMessage. We'll display the model used and their accuracy when showing these flags in the review queue and adjust the latter after staff performs an action, tracking a global accuracy per existing model in a separate table. * FEATURE: Dedicated reviewables for AI flags * Store and adjust model accuracy * Display accuracy in reviewable templates
2023-03-07 13:39:28 -05:00
title: "AI-Flagged post"
FIX: Fix reviewable title translations (#18)
2023-03-20 09:09:20 -04:00
reviewable_ai_chat_message:
FEATURE: Use dedicated reviewables for AI flags. (#4) This change adds two new reviewable types: ReviewableAIPost and ReviewableAIChatMessage. They have the same actions as their existing counterparts: ReviewableFlaggedPost and ReviewableChatMessage. We'll display the model used and their accuracy when showing these flags in the review queue and adjust the latter after staff performs an action, tracking a global accuracy per existing model in a separate table. * FEATURE: Dedicated reviewables for AI flags * Store and adjust model accuracy * Display accuracy in reviewable templates
2023-03-07 13:39:28 -05:00
title: "AI-Flagged chat message"