Sam 0d7f353284
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.
2024-11-19 09:22:39 +11:00

98 lines
2.3 KiB
Ruby

# frozen_string_literal: true
module DiscourseAi
module Completions
module Dialects
class Ollama < Dialect
class << self
def can_translate?(model_provider)
model_provider == "ollama"
end
end
def native_tool_support?
enable_native_tool?
end
def max_prompt_tokens
llm_model.max_prompt_tokens
end
private
def tools_dialect
if enable_native_tool?
@tools_dialect ||= DiscourseAi::Completions::Dialects::OllamaTools.new(prompt.tools)
else
super
end
end
def tokenizer
llm_model.tokenizer_class
end
def model_msg(msg)
{ role: "assistant", content: msg[:content] }
end
def tool_call_msg(msg)
if enable_native_tool?
tools_dialect.from_raw_tool_call(msg)
else
super
end
end
def tool_msg(msg)
if enable_native_tool?
tools_dialect.from_raw_tool(msg)
else
super
end
end
def system_msg(msg)
msg = { role: "system", content: msg[:content] }
if tools_dialect.instructions.present?
msg[:content] = msg[:content].dup << "\n\n#{tools_dialect.instructions}"
end
msg
end
def enable_native_tool?
return @enable_native_tool if defined?(@enable_native_tool)
@enable_native_tool = llm_model.lookup_custom_param("enable_native_tool")
end
def user_msg(msg)
user_message = { role: "user", content: msg[:content] }
encoded_uploads = prompt.encoded_uploads(msg)
if encoded_uploads.present?
images =
encoded_uploads
.map do |upload|
if upload[:mime_type].start_with?("image/")
upload[:base64]
else
nil
end
end
.compact
user_message[:images] = images if images.present?
end
# TODO: Add support for user messages with embedded user ids
user_message
end
end
end
end
end