discourse-ai/config/locales/client.en.yml

575 lines
26 KiB
YAML
Raw Normal View History

2023-02-17 09:33:47 -05:00
en:
admin_js:
admin:
api:
scopes:
descriptions:
discourse_ai:
search: "Allows AI search"
stream_completion: "Allows streaming AI persona completions"
site_settings:
categories:
discourse_ai: "Discourse AI"
dashboard:
emotion:
title: "Emotion"
description: "The table lists a count of posts classified with a determined emotion. Classified with the model 'SamLowe/roberta-base-go_emotions'."
2023-02-17 09:33:47 -05:00
js:
discourse_automation:
scriptables:
llm_report:
fields:
sender:
label: "Sender"
description: "The user that will send the report"
receivers:
label: "Receivers"
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"
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"
2024-01-18 10:38:29 -05:00
description: "Filter topics only to these categories"
tags:
label: "Tags"
description: "Filter topics only to these tags"
exclude_tags:
label: "Exclude Tags"
description: "Exclude topics with these tags"
exclude_categories:
label: "Exclude Categories"
description: "Exclude topics with these categories"
allow_secure_categories:
label: "Allow secure categories"
description: "Allow the report to be generated for topics in secure categories"
suppress_notifications:
label: "Suppress Notifications"
description: "Suppress notifications the report may generate by transforming to content. This will remap mentions and internal links."
debug_mode:
label: "Debug Mode"
description: "Enable debug mode to see the raw input and output of the LLM"
priority_group:
label: "Priority Group"
description: "Prioritize content from this group in the report"
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)"
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"
max_post_tokens:
label: "Max Post Tokens"
description: "The maximum number of tokens to scan using LLM triage"
stop_sequences:
label: "Stop Sequences"
description: "Instruct the model to halt token generation when arriving at one of these values"
search_for_text:
label: "Search for text"
description: "If the following text appears in the LLM reply, apply these 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 the 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 not visible to the public if triggered"
flag_type:
label: "Flag type"
description: "Type of flag to apply to the post (spam or simply raise for review)"
flag_post:
label: "Flag post"
description: "Flags post (either as spam or for review)"
include_personal_messages:
label: "Include personal messages"
description: "Also scan and triage personal messages"
model:
label: "Model"
description: "Language model used for triage"
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"
2024-05-27 13:49:24 -04:00
modals:
select_option: "Select an option..."
2024-12-11 17:17:25 -05:00
spam:
short_title: "Spam"
title: "Configure spam handling"
select_llm: "Select LLM"
custom_instructions: "Custom instructions"
custom_instructions_help: "Custom instructions specific to your site to help guide the AI in identifying spam, e.g. 'Be more aggressive about scanning posts not in English'."
last_seven_days: "Last 7 days"
scanned_count: "Posts scanned"
false_positives: "Incorrectly flagged"
false_negatives: "Missed spam"
spam_detected: "Spam detected"
custom_instructions_placeholder: "Site-specific instructions for the AI to help identify spam more accurately"
enable: "Enable"
spam_tip: "AI spam detection will scan the first 3 posts by all new users on public topics. It will flag them for review and block users if they are likely spam."
settings_saved: "Settings saved"
spam_description: "Identifies potential spam using the selected LLM and flags it for site moderators to inspect in the review queue"
no_llms: "No LLMs available"
test_button: "Test..."
save_button: "Save changes"
test_modal:
title: "Test spam detection"
post_url_label: "Post URL or ID"
post_url_placeholder: "https://your-forum.com/t/topic/123/4 or post ID"
result: "Result"
scan_log: "Scan log"
run: "Run test"
spam: "Spam"
not_spam: "Not spam"
stat_tooltips:
incorrectly_flagged: "Items that the AI bot flagged as spam where moderators disagreed"
missed_spam: "Items flagged by the community as spam that were not detected by the AI bot, which moderators agreed with"
2024-12-11 17:17:25 -05:00
usage:
short_title: "Usage"
summary: "Summary"
total_tokens: "Total tokens"
tokens_over_time: "Tokens over time"
features_breakdown: "Usage per feature"
feature: "Feature"
usage_count: "Usage count"
model: "Model"
models_breakdown: "Usage per model"
users_breakdown: "Usage per user"
all_features: "All features"
all_models: "All models"
username: "Username"
total_requests: "Total requests"
request_tokens: "Request tokens"
response_tokens: "Response tokens"
net_request_tokens: "Net request tokens"
cached_tokens: "Cached tokens"
cached_request_tokens: "Cached request tokens"
no_users: "No user usage data found"
no_models: "No model usage data found"
no_features: "No feature usage data found"
subheader_description: "Tokens are the basic units that LLMs use to understand and generate text, usage data may affect costs."
stat_tooltips:
total_requests: "All requests made to LLMs through Discourse"
total_tokens: "All the tokens used when prompting an LLM"
request_tokens: "Tokens used when the LLM tries to understand what you are saying"
response_tokens: "Tokens used when the LLM responds to your prompt"
cached_tokens: "Previously processed request tokens that the LLM reuses to optimize performance and cost"
periods:
last_day: "Last 24 hours"
last_week: "Last week"
last_month: "Last month"
custom: "Custom..."
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:
tool_strategies:
all: "Apply to all replies"
replies:
one: "Apply to first reply only"
other: "Apply to first %{count} replies"
back: "Back"
name: "Name"
edit: "Edit"
description: "Description"
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)"
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. Supported by latest models from Anthropic, Google, and OpenAI.
vision_max_pixels: Supported image size
vision_max_pixel_sizes:
low: Low quality - cheapest (256x256)
medium: Medium quality (512x512)
high: High quality - slowest (1024x1024)
tool_details: Show tool details
tool_details_help: Will show end users details on which tools the language model has triggered.
mentionable: Allow mentions
mentionable_help: If enabled, users in allowed groups can mention this user in posts, the AI will respond as this persona.
user: User
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.
system_prompt: System prompt
forced_tool_strategy: Forced tool strategy
allow_chat_direct_messages: "Allow chat direct messages"
allow_chat_direct_messages_help: "If enabled, users in allowed groups can send direct messages to this persona."
allow_chat_channel_mentions: "Allow chat channel mentions"
allow_chat_channel_mentions_help: "If enabled, users in allowed groups can mention this persona in chat channels."
allow_personal_messages: "Allow personal messages"
allow_personal_messages_help: "If enabled, users in allowed groups can send personal messages to this persona."
allow_topic_mentions: "Allow topic mentions"
allow_topic_mentions_help: "If enabled, users in allowed groups can mention this persona in topics."
force_default_llm: "Always use default language model"
save: "Save"
saved: "Persona saved"
enabled: "Enabled?"
tools: "Enabled tools"
FEATURE: AI artifacts (#898) This is a significant PR that introduces AI Artifacts functionality to the discourse-ai plugin along with several other improvements. Here are the key changes: 1. AI Artifacts System: - Adds a new `AiArtifact` model and database migration - Allows creation of web artifacts with HTML, CSS, and JavaScript content - Introduces security settings (`strict`, `lax`, `disabled`) for controlling artifact execution - Implements artifact rendering in iframes with sandbox protection - New `CreateArtifact` tool for AI to generate interactive content 2. Tool System Improvements: - Adds support for partial tool calls, allowing incremental updates during generation - Better handling of tool call states and progress tracking - Improved XML tool processing with CDATA support - Fixes for tool parameter handling and duplicate invocations 3. LLM Provider Updates: - Updates for Anthropic Claude models with correct token limits - Adds support for native/XML tool modes in Gemini integration - Adds new model configurations including Llama 3.1 models - Improvements to streaming response handling 4. UI Enhancements: - New artifact viewer component with expand/collapse functionality - Security controls for artifact execution (click-to-run in strict mode) - Improved dialog and response handling - Better error management for tool execution 5. Security Improvements: - Sandbox controls for artifact execution - Public/private artifact sharing controls - Security settings to control artifact behavior - CSP and frame-options handling for artifacts 6. Technical Improvements: - Better post streaming implementation - Improved error handling in completions - Better memory management for partial tool calls - Enhanced testing coverage 7. Configuration: - New site settings for artifact security - Extended LLM model configurations - Additional tool configuration options This PR significantly enhances the plugin's capabilities for generating and displaying interactive content while maintaining security and providing flexible configuration options for administrators.
2024-11-18 17:22:39 -05:00
forced_tools: "Forced tools"
allowed_groups: "Allowed groups"
confirm_delete: "Are you sure you want to delete this persona?"
new: "New persona"
no_personas: "You have not created any personas yet"
title: "Personas"
short_title: "Personas"
delete: "Delete"
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)"
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."
tool_options: "Tool options"
rag_conversation_chunks: "Search conversation chunks"
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."
persona_description: "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."
rag:
options:
rag_chunk_tokens: "Upload chunk tokens"
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)"
rag_chunk_overlap_tokens: "Upload chunk overlap tokens"
rag_chunk_overlap_tokens_help: "The number of tokens to overlap between chunks in the RAG model. (changing will re-index all uploads)"
show_indexing_options: "Show upload options"
hide_indexing_options: "Hide upload options"
uploads:
title: "Uploads"
description: "Uploaded files should be formatted as plaintext (.txt) or markdown (.md)."
button: "Add files"
filter: "Filter uploads"
indexed: "Indexed"
indexing: "Indexing"
uploaded: "Ready to be indexed"
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: custom user defined tools (#677) Introduces custom AI tools functionality. 1. Why it was added: The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform. 2. What it does: - Introduces a new `AiTool` model for storing custom AI tools - Adds CRUD (Create, Read, Update, Delete) operations for AI tools - Implements a tool runner system for executing custom tool scripts - Integrates custom tools with existing AI personas - Provides a user interface for managing custom tools in the admin panel 3. Possible use cases: - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...) - Allowing administrators to add new functionalities to AI assistants without modifying core code - Implementing domain-specific tools for particular communities or industries 4. Code structure: The PR introduces several new files and modifies existing ones: a. Models: - `app/models/ai_tool.rb`: Defines the AiTool model - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools b. Controllers: - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools c. Views and Components: - New Ember.js components for tool management in the admin interface - Updates to existing AI persona management components to support custom tools d. Core functionality: - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class e. Routes and configurations: - Updates to route configurations to include new AI tool management pages f. Migrations: - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table g. Tests: - New test files for AI tool functionality and integration The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools. Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs. Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 03:27:40 -04:00
tools:
back: "Back"
FEATURE: custom user defined tools (#677) Introduces custom AI tools functionality. 1. Why it was added: The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform. 2. What it does: - Introduces a new `AiTool` model for storing custom AI tools - Adds CRUD (Create, Read, Update, Delete) operations for AI tools - Implements a tool runner system for executing custom tool scripts - Integrates custom tools with existing AI personas - Provides a user interface for managing custom tools in the admin panel 3. Possible use cases: - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...) - Allowing administrators to add new functionalities to AI assistants without modifying core code - Implementing domain-specific tools for particular communities or industries 4. Code structure: The PR introduces several new files and modifies existing ones: a. Models: - `app/models/ai_tool.rb`: Defines the AiTool model - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools b. Controllers: - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools c. Views and Components: - New Ember.js components for tool management in the admin interface - Updates to existing AI persona management components to support custom tools d. Core functionality: - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class e. Routes and configurations: - Updates to route configurations to include new AI tool management pages f. Migrations: - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table g. Tests: - New test files for AI tool functionality and integration The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools. Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs. Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 03:27:40 -04:00
short_title: "Tools"
no_tools: "You have not created any tools yet"
FEATURE: custom user defined tools (#677) Introduces custom AI tools functionality. 1. Why it was added: The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform. 2. What it does: - Introduces a new `AiTool` model for storing custom AI tools - Adds CRUD (Create, Read, Update, Delete) operations for AI tools - Implements a tool runner system for executing custom tool scripts - Integrates custom tools with existing AI personas - Provides a user interface for managing custom tools in the admin panel 3. Possible use cases: - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...) - Allowing administrators to add new functionalities to AI assistants without modifying core code - Implementing domain-specific tools for particular communities or industries 4. Code structure: The PR introduces several new files and modifies existing ones: a. Models: - `app/models/ai_tool.rb`: Defines the AiTool model - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools b. Controllers: - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools c. Views and Components: - New Ember.js components for tool management in the admin interface - Updates to existing AI persona management components to support custom tools d. Core functionality: - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class e. Routes and configurations: - Updates to route configurations to include new AI tool management pages f. Migrations: - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table g. Tests: - New test files for AI tool functionality and integration The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools. Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs. Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 03:27:40 -04:00
name: "Name"
subheader_description: "Tools extend the capabilities of AI bots with user-defined JavaScript functions."
new: "New tool"
FEATURE: custom user defined tools (#677) Introduces custom AI tools functionality. 1. Why it was added: The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform. 2. What it does: - Introduces a new `AiTool` model for storing custom AI tools - Adds CRUD (Create, Read, Update, Delete) operations for AI tools - Implements a tool runner system for executing custom tool scripts - Integrates custom tools with existing AI personas - Provides a user interface for managing custom tools in the admin panel 3. Possible use cases: - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...) - Allowing administrators to add new functionalities to AI assistants without modifying core code - Implementing domain-specific tools for particular communities or industries 4. Code structure: The PR introduces several new files and modifies existing ones: a. Models: - `app/models/ai_tool.rb`: Defines the AiTool model - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools b. Controllers: - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools c. Views and Components: - New Ember.js components for tool management in the admin interface - Updates to existing AI persona management components to support custom tools d. Core functionality: - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class e. Routes and configurations: - Updates to route configurations to include new AI tool management pages f. Migrations: - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table g. Tests: - New test files for AI tool functionality and integration The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools. Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs. Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 03:27:40 -04:00
name_help: "The unique name of the tool as used by the language model"
description: "Description"
description_help: "A clear description of the tool's purpose for the language model"
summary: "Summary"
summary_help: "Summary of tools purpose to be displayed to end users"
script: "Script"
parameters: "Parameters"
save: "Save"
add_parameter: "Add Parameter"
parameter_required: "Required"
parameter_enum: "Enum"
parameter_name: "Parameter name"
parameter_description: "Parameter description"
enum_value: "Enum value"
add_enum_value: "Add enum value"
FEATURE: custom user defined tools (#677) Introduces custom AI tools functionality. 1. Why it was added: The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform. 2. What it does: - Introduces a new `AiTool` model for storing custom AI tools - Adds CRUD (Create, Read, Update, Delete) operations for AI tools - Implements a tool runner system for executing custom tool scripts - Integrates custom tools with existing AI personas - Provides a user interface for managing custom tools in the admin panel 3. Possible use cases: - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...) - Allowing administrators to add new functionalities to AI assistants without modifying core code - Implementing domain-specific tools for particular communities or industries 4. Code structure: The PR introduces several new files and modifies existing ones: a. Models: - `app/models/ai_tool.rb`: Defines the AiTool model - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools b. Controllers: - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools c. Views and Components: - New Ember.js components for tool management in the admin interface - Updates to existing AI persona management components to support custom tools d. Core functionality: - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class e. Routes and configurations: - Updates to route configurations to include new AI tool management pages f. Migrations: - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table g. Tests: - New test files for AI tool functionality and integration The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools. Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs. Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 03:27:40 -04:00
edit: "Edit"
test: "Run test"
FEATURE: custom user defined tools (#677) Introduces custom AI tools functionality. 1. Why it was added: The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform. 2. What it does: - Introduces a new `AiTool` model for storing custom AI tools - Adds CRUD (Create, Read, Update, Delete) operations for AI tools - Implements a tool runner system for executing custom tool scripts - Integrates custom tools with existing AI personas - Provides a user interface for managing custom tools in the admin panel 3. Possible use cases: - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...) - Allowing administrators to add new functionalities to AI assistants without modifying core code - Implementing domain-specific tools for particular communities or industries 4. Code structure: The PR introduces several new files and modifies existing ones: a. Models: - `app/models/ai_tool.rb`: Defines the AiTool model - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools b. Controllers: - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools c. Views and Components: - New Ember.js components for tool management in the admin interface - Updates to existing AI persona management components to support custom tools d. Core functionality: - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class e. Routes and configurations: - Updates to route configurations to include new AI tool management pages f. Migrations: - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table g. Tests: - New test files for AI tool functionality and integration The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools. Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs. Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 03:27:40 -04:00
delete: "Delete"
saved: "Tool saved"
presets: "Select a preset..."
confirm_delete: "Are you sure you want to delete this tool?"
FEATURE: custom user defined tools (#677) Introduces custom AI tools functionality. 1. Why it was added: The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform. 2. What it does: - Introduces a new `AiTool` model for storing custom AI tools - Adds CRUD (Create, Read, Update, Delete) operations for AI tools - Implements a tool runner system for executing custom tool scripts - Integrates custom tools with existing AI personas - Provides a user interface for managing custom tools in the admin panel 3. Possible use cases: - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...) - Allowing administrators to add new functionalities to AI assistants without modifying core code - Implementing domain-specific tools for particular communities or industries 4. Code structure: The PR introduces several new files and modifies existing ones: a. Models: - `app/models/ai_tool.rb`: Defines the AiTool model - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools b. Controllers: - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools c. Views and Components: - New Ember.js components for tool management in the admin interface - Updates to existing AI persona management components to support custom tools d. Core functionality: - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class e. Routes and configurations: - Updates to route configurations to include new AI tool management pages f. Migrations: - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table g. Tests: - New test files for AI tool functionality and integration The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools. Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs. Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 03:27:40 -04:00
next:
title: "Next"
test_modal:
title: "Test AI tool"
run: "Run test"
result: "Test result"
FEATURE: custom user defined tools (#677) Introduces custom AI tools functionality. 1. Why it was added: The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform. 2. What it does: - Introduces a new `AiTool` model for storing custom AI tools - Adds CRUD (Create, Read, Update, Delete) operations for AI tools - Implements a tool runner system for executing custom tool scripts - Integrates custom tools with existing AI personas - Provides a user interface for managing custom tools in the admin panel 3. Possible use cases: - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...) - Allowing administrators to add new functionalities to AI assistants without modifying core code - Implementing domain-specific tools for particular communities or industries 4. Code structure: The PR introduces several new files and modifies existing ones: a. Models: - `app/models/ai_tool.rb`: Defines the AiTool model - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools b. Controllers: - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools c. Views and Components: - New Ember.js components for tool management in the admin interface - Updates to existing AI persona management components to support custom tools d. Core functionality: - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class e. Routes and configurations: - Updates to route configurations to include new AI tool management pages f. Migrations: - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table g. Tests: - New test files for AI tool functionality and integration The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools. Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs. Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 03:27:40 -04:00
llms:
short_title: "LLMs"
no_llms: "No LLMs yet"
new: "New model"
display_name: "Name"
name: "Model id"
provider: "Provider"
tokenizer: "Tokenizer"
max_prompt_tokens: "Number of tokens for the prompt"
url: "URL of the service hosting the model"
api_key: "API Key of the service hosting the model"
enabled_chat_bot: "Allow AI bot selector"
vision_enabled: "Vision enabled"
ai_bot_user: "AI bot User"
save: "Save"
edit: "Edit"
saved: "LLM model saved"
back: "Back"
confirm_delete: Are you sure you want to delete this model?
delete: Delete
seeded_warning: "This model is pre-configured on your site and cannot be edited."
usage:
ai_bot: "AI bot"
ai_helper: "Helper"
ai_persona: "Persona (%{persona})"
ai_summarization: "Summarize"
ai_embeddings_semantic_search: "AI search"
2024-12-11 17:17:25 -05:00
ai_spam: "Spam"
in_use_warning:
one: "This model is currently used by %{settings}. If misconfigured, the feature won't work as expected."
other: "This model is currently used by the following: %{settings}. If misconfigured, features won't work as expected. "
model_description:
none: "General settings that work for most language models"
anthropic-claude-3-5-sonnet: "Anthropic's most intelligent model"
FEATURE: AI artifacts (#898) This is a significant PR that introduces AI Artifacts functionality to the discourse-ai plugin along with several other improvements. Here are the key changes: 1. AI Artifacts System: - Adds a new `AiArtifact` model and database migration - Allows creation of web artifacts with HTML, CSS, and JavaScript content - Introduces security settings (`strict`, `lax`, `disabled`) for controlling artifact execution - Implements artifact rendering in iframes with sandbox protection - New `CreateArtifact` tool for AI to generate interactive content 2. Tool System Improvements: - Adds support for partial tool calls, allowing incremental updates during generation - Better handling of tool call states and progress tracking - Improved XML tool processing with CDATA support - Fixes for tool parameter handling and duplicate invocations 3. LLM Provider Updates: - Updates for Anthropic Claude models with correct token limits - Adds support for native/XML tool modes in Gemini integration - Adds new model configurations including Llama 3.1 models - Improvements to streaming response handling 4. UI Enhancements: - New artifact viewer component with expand/collapse functionality - Security controls for artifact execution (click-to-run in strict mode) - Improved dialog and response handling - Better error management for tool execution 5. Security Improvements: - Sandbox controls for artifact execution - Public/private artifact sharing controls - Security settings to control artifact behavior - CSP and frame-options handling for artifacts 6. Technical Improvements: - Better post streaming implementation - Improved error handling in completions - Better memory management for partial tool calls - Enhanced testing coverage 7. Configuration: - New site settings for artifact security - Extended LLM model configurations - Additional tool configuration options This PR significantly enhances the plugin's capabilities for generating and displaying interactive content while maintaining security and providing flexible configuration options for administrators.
2024-11-18 17:22:39 -05:00
anthropic-claude-3-5-haiku: "Fast and cost-effective"
anthropic-claude-3-opus: "Excels at writing and complex tasks"
google-gemini-1-5-pro: "Mid-sized multimodal model capable of a wide range of tasks"
google-gemini-1-5-flash: "Lightweight, fast, and cost-efficient with multimodal reasoning"
open_ai-gpt-4-turbo: "Previous generation high-intelligence model"
open_ai-gpt-4o: "High intelligence model for complex, multi-step tasks"
open_ai-gpt-4o-mini: "Affordable and fast small model for lightweight tasks"
FEATURE: AI artifacts (#898) This is a significant PR that introduces AI Artifacts functionality to the discourse-ai plugin along with several other improvements. Here are the key changes: 1. AI Artifacts System: - Adds a new `AiArtifact` model and database migration - Allows creation of web artifacts with HTML, CSS, and JavaScript content - Introduces security settings (`strict`, `lax`, `disabled`) for controlling artifact execution - Implements artifact rendering in iframes with sandbox protection - New `CreateArtifact` tool for AI to generate interactive content 2. Tool System Improvements: - Adds support for partial tool calls, allowing incremental updates during generation - Better handling of tool call states and progress tracking - Improved XML tool processing with CDATA support - Fixes for tool parameter handling and duplicate invocations 3. LLM Provider Updates: - Updates for Anthropic Claude models with correct token limits - Adds support for native/XML tool modes in Gemini integration - Adds new model configurations including Llama 3.1 models - Improvements to streaming response handling 4. UI Enhancements: - New artifact viewer component with expand/collapse functionality - Security controls for artifact execution (click-to-run in strict mode) - Improved dialog and response handling - Better error management for tool execution 5. Security Improvements: - Sandbox controls for artifact execution - Public/private artifact sharing controls - Security settings to control artifact behavior - CSP and frame-options handling for artifacts 6. Technical Improvements: - Better post streaming implementation - Improved error handling in completions - Better memory management for partial tool calls - Enhanced testing coverage 7. Configuration: - New site settings for artifact security - Extended LLM model configurations - Additional tool configuration options This PR significantly enhances the plugin's capabilities for generating and displaying interactive content while maintaining security and providing flexible configuration options for administrators.
2024-11-18 17:22:39 -05:00
open_ai-o1-mini: "Cost-efficient reasoning model"
open_ai-o1-preview: "Open AI's most capabale reasoning model"
samba_nova-Meta-Llama-3-1-8B-Instruct: "Efficient lightweight multilingual model"
samba_nova-Meta-Llama-3-1-70B-Instruct": "Powerful multipurpose model"
mistral-mistral-large-latest: "Mistral's most powerful model"
mistral-pixtral-large-latest: "Mistral's most powerful vision capable model"
configured:
title: "Configured LLMs"
preconfigured_llms: "Select your LLM"
preconfigured:
title_no_llms: "Select a template to get started"
title: "Unconfigured LLM templates"
description: "LLMs (Large Language Models) are AI tools optimized for tasks like summarizing content, generating reports, automating customer interactions, and facilitating forum moderation and insights."
fake: "Manual configuration"
button: "Set up"
next:
title: "Next"
tests:
title: "Run test"
2024-05-21 12:35:50 -04:00
running: "Running test..."
success: "Success!"
failure: "Trying to contact the model returned this error: %{error}"
hints:
max_prompt_tokens: "Max numbers of tokens for the prompt. As a rule of thumb, this should be 50% of the model's context window."
name: "We include this in the API call to specify which model we'll use"
vision_enabled: "If enabled, the AI will attempt to understand images. It depends on the model being used supporting vision. Supported by latest models from Anthropic, Google, and OpenAI."
enabled_chat_bot: "If enabled, users can select this model when creating PMs with the AI bot"
providers:
aws_bedrock: "AWS Bedrock"
anthropic: "Anthropic"
vllm: "vLLM"
hugging_face: "Hugging Face"
cohere: "Cohere"
open_ai: "OpenAI"
google: "Google"
azure: "Azure"
ollama: "Ollama"
CDCK: "CDCK"
samba_nova: "SambaNova"
mistral: "Mistral"
open_router: "OpenRouter"
fake: "Custom"
FEATURE: custom user defined tools (#677) Introduces custom AI tools functionality. 1. Why it was added: The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform. 2. What it does: - Introduces a new `AiTool` model for storing custom AI tools - Adds CRUD (Create, Read, Update, Delete) operations for AI tools - Implements a tool runner system for executing custom tool scripts - Integrates custom tools with existing AI personas - Provides a user interface for managing custom tools in the admin panel 3. Possible use cases: - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...) - Allowing administrators to add new functionalities to AI assistants without modifying core code - Implementing domain-specific tools for particular communities or industries 4. Code structure: The PR introduces several new files and modifies existing ones: a. Models: - `app/models/ai_tool.rb`: Defines the AiTool model - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools b. Controllers: - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools c. Views and Components: - New Ember.js components for tool management in the admin interface - Updates to existing AI persona management components to support custom tools d. Core functionality: - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class e. Routes and configurations: - Updates to route configurations to include new AI tool management pages f. Migrations: - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table g. Tests: - New test files for AI tool functionality and integration The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools. Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs. Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 03:27:40 -04:00
provider_fields:
access_key_id: "AWS Bedrock access key ID"
region: "AWS Bedrock region"
organization: "Optional OpenAI organization ID"
disable_system_prompt: "Disable system message in prompts"
enable_native_tool: "Enable native tool support"
disable_native_tools: "Disable native tool support (use XML based tools)"
provider_order: "Provider order (comma delimited list)"
provider_quantizations: "Order of provider quantizations (comma delimited list eg: fp16,fp8)"
related_topics:
title: "Related topics"
pill: "Related"
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."
suggest: "Suggest with AI"
suggest_errors:
too_many_tags:
one: "You can only have up to %{count} tag"
other: "You can only have up to %{count} tags"
no_suggestions: "No suggestions available"
missing_content: "Please enter some content to generate suggestions."
2023-08-23 13:35:40 -04:00
context_menu:
trigger: "Ask AI"
loading: "AI is generating"
2023-08-23 13:35:40 -04:00
cancel: "Cancel"
regen: "Try Again"
2023-08-24 20:49:24 -04:00
confirm: "Confirm"
discard: "Discard"
changes: "Suggested edits"
custom_prompt:
title: "Custom prompt"
placeholder: "Enter a custom prompt..."
submit: "Send prompt"
translate_prompt: "Translate to %{language}"
post_options_menu:
trigger: "Ask AI"
2023-12-05 15:33:10 -05:00
title: "Ask AI"
loading: "AI is generating"
close: "Close"
copy: "Copy"
copied: "Copied!"
cancel: "Cancel"
insert_footnote: "Add footnote"
footnote_disabled: "Automatic insertion disabled, click copy button and edit it in manually"
footnote_credits: "Explanation by AI"
fast_edit:
suggest_button: "Suggest edit"
thumbnail_suggestions:
title: "Suggested thumbnails"
select: "Select"
selected: "Selected"
image_caption:
button_label: "Caption with AI"
generating: "Generating caption..."
credits: "Captioned by AI"
save_caption: "Save"
automatic_caption_setting: "Enable auto caption"
2024-05-27 13:49:24 -04:00
automatic_caption_loading: "Captioning images..."
automatic_caption_dialog:
prompt: "This post contains non-captioned images. Would you like to enable automatic captions on image uploads? (This can be changed in your preferences later)"
2024-05-27 13:49:24 -04:00
confirm: "Enable"
cancel: "Don't ask again"
no_content_error: "Add content first to perform AI actions on it"
reviewables:
model_used: "Model used:"
accuracy: "Accuracy:"
embeddings:
semantic_search: "Topics (Semantic)"
semantic_search_loading: "Searching for more results using AI"
semantic_search_results:
toggle: "Showing %{count} results found using AI"
toggle_hidden: "Hiding %{count} results found using AI"
none: "Sorry, our AI search found no matching topics"
new: "Press 'search' to begin looking for new results with AI"
ai_generated_result: "Search result found using AI"
quick_search:
suffix: "in all topics and posts with AI"
FEATURE: AI artifacts (#898) This is a significant PR that introduces AI Artifacts functionality to the discourse-ai plugin along with several other improvements. Here are the key changes: 1. AI Artifacts System: - Adds a new `AiArtifact` model and database migration - Allows creation of web artifacts with HTML, CSS, and JavaScript content - Introduces security settings (`strict`, `lax`, `disabled`) for controlling artifact execution - Implements artifact rendering in iframes with sandbox protection - New `CreateArtifact` tool for AI to generate interactive content 2. Tool System Improvements: - Adds support for partial tool calls, allowing incremental updates during generation - Better handling of tool call states and progress tracking - Improved XML tool processing with CDATA support - Fixes for tool parameter handling and duplicate invocations 3. LLM Provider Updates: - Updates for Anthropic Claude models with correct token limits - Adds support for native/XML tool modes in Gemini integration - Adds new model configurations including Llama 3.1 models - Improvements to streaming response handling 4. UI Enhancements: - New artifact viewer component with expand/collapse functionality - Security controls for artifact execution (click-to-run in strict mode) - Improved dialog and response handling - Better error management for tool execution 5. Security Improvements: - Sandbox controls for artifact execution - Public/private artifact sharing controls - Security settings to control artifact behavior - CSP and frame-options handling for artifacts 6. Technical Improvements: - Better post streaming implementation - Improved error handling in completions - Better memory management for partial tool calls - Enhanced testing coverage 7. Configuration: - New site settings for artifact security - Extended LLM model configurations - Additional tool configuration options This PR significantly enhances the plugin's capabilities for generating and displaying interactive content while maintaining security and providing flexible configuration options for administrators.
2024-11-18 17:22:39 -05:00
ai_artifact:
expand_view_label: "Expand view"
collapse_view_label: "Exit Fullscreen (ESC or Back button)"
FEATURE: AI artifacts (#898) This is a significant PR that introduces AI Artifacts functionality to the discourse-ai plugin along with several other improvements. Here are the key changes: 1. AI Artifacts System: - Adds a new `AiArtifact` model and database migration - Allows creation of web artifacts with HTML, CSS, and JavaScript content - Introduces security settings (`strict`, `lax`, `disabled`) for controlling artifact execution - Implements artifact rendering in iframes with sandbox protection - New `CreateArtifact` tool for AI to generate interactive content 2. Tool System Improvements: - Adds support for partial tool calls, allowing incremental updates during generation - Better handling of tool call states and progress tracking - Improved XML tool processing with CDATA support - Fixes for tool parameter handling and duplicate invocations 3. LLM Provider Updates: - Updates for Anthropic Claude models with correct token limits - Adds support for native/XML tool modes in Gemini integration - Adds new model configurations including Llama 3.1 models - Improvements to streaming response handling 4. UI Enhancements: - New artifact viewer component with expand/collapse functionality - Security controls for artifact execution (click-to-run in strict mode) - Improved dialog and response handling - Better error management for tool execution 5. Security Improvements: - Sandbox controls for artifact execution - Public/private artifact sharing controls - Security settings to control artifact behavior - CSP and frame-options handling for artifacts 6. Technical Improvements: - Better post streaming implementation - Improved error handling in completions - Better memory management for partial tool calls - Enhanced testing coverage 7. Configuration: - New site settings for artifact security - Extended LLM model configurations - Additional tool configuration options This PR significantly enhances the plugin's capabilities for generating and displaying interactive content while maintaining security and providing flexible configuration options for administrators.
2024-11-18 17:22:39 -05:00
click_to_run_label: "Run Artifact"
ai_bot:
pm_warning: "AI chatbot messages are monitored regularly by moderators."
cancel_streaming: "Stop reply"
default_pm_prefix: "[Untitled AI bot PM]"
shortcut_title: "Start a PM with an AI bot"
share: "Copy AI conversation"
2023-12-29 10:26:03 -05:00
conversation_shared: "Conversation copied"
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:"
request: "Request"
response: "Response"
next_log: "Next"
previous_log: "Previous"
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"
ai_label: "AI"
ai_title: "Conversation with AI"
share_modal:
title: "Copy AI conversation"
copy: "Copy"
context: "Interactions to share:"
share_tip: "Alternatively, you can share the entire conversation"
bot_names:
fake: "Fake Test Bot"
claude-3-opus: "Claude 3 Opus"
claude-3-sonnet: "Claude 3 Sonnet"
claude-3-haiku: "Claude 3 Haiku"
cohere-command-r-plus: "Cohere Command R Plus"
gpt-4: "GPT-4"
gpt-4-turbo: "GPT-4 Turbo"
gpt-4o: "GPT-4 Omni"
gpt-3:
5-turbo: "GPT-3.5"
claude-2: "Claude 2"
gemini-1:
5-pro: "Gemini"
mixtral-8x7B-Instruct-V0:
"1": "Mixtral-8x7B V0.1"
sentiments:
dashboard:
title: "Sentiment"
summarization:
chat:
title: "Summarize messages"
description: "Select an option below to summarize the conversation sent during the desired timeframe."
summarize: "Summarize"
since:
one: "Last hour"
other: "Last %{count} hours"
topic:
title: "Topic summary"
close: "Close summary panel"
2024-11-19 15:33:34 -05:00
topic_list_layout:
button:
compact: "Compact"
expanded: "Expanded"
expanded_description: "with AI summaries"
review:
types:
reviewable_ai_post:
title: "AI-Flagged post"
reviewable_ai_chat_message:
title: "AI-Flagged chat message"