This guide explains how to enable and configure the AI search feature, which is part of the Discourse AI plugin.
Required user level: Administrator
Similar to Related topics, AI search helps you find the most relevant topics using semantic textual similarity that are beyond an exact keyword match used by traditional search. This results in the discovery of topics that are non-exact matches but still relevant to the initial search. If you can’t find what you’re looking for, AI search is here to help!
Features
- Semantic textual similarity: going beyond just a keyword match and using semantic analysis to find textual similarity
- AI quick search
- Toggled on/off for AI search in full-page search
- Results indicated by icon
- Applicable to both anonymous and logged-in users
Enabling AI Search
Prerequisites
To use AI Search you will need Embeddings and a Large Language Model (LLM).
Embeddings
If you are on our hosting, we will provide a default option. For self-hosters follow the guide at Discourse AI - Embeddings
Large Language Model (LLM)
Discourse hosted customers and self-hosters must configure at least one Large Language Model (LLM) from a provider.
To get started you can configure them through the Discourse AI - Large Language Model (LLM) settings page.
- OpenAI
- Anthropic
- Azure OpenAI
- AWS Bedrock with Anthropic access
- HuggingFace Endpoints with Llama2-like model
- Self-Hosting an OpenSource LLM for DiscourseAI
- Google Gemini
Configuration
- Go to
Admin
settings->Plugins
→ search or finddiscourse-ai
and make sure it’s enabled - Enable
ai_embeddings_enabled
for Embeddings - Enable
ai_embeddings_semantic_search_enabled
to activate AI search
Technical FAQ
Expand for an outline of the AI search logic
mermaid height=255,auto
sequenceDiagram
User->>+Discourse: Search "gamification"
Discourse->>+LLM: Create an article about "gamification" in a forum about<br> "Discourse, an open source Internet forum system."
LLM->>+Discourse: Gamification involves applying game design elements like<br> points, badges, levels, and leaderboards to non-game contexts...
Discourse->>+EmbeddingsAPI: Generate Embeddings for "Gamification involves applying game design..."
EmbeddingsAPI->>+Discourse: [0.123, -0.321...]
Discourse->>+PostgreSQL: Give me the nearest topics for [0.123, -0.321...]
PostgreSQL->>+Discourse: Topics: [1, 5, 10, 50]
Discourse->>+User: Topics: [1, 5, 10, 50]
How does AI Search work?
- The initial search query is run through an LLM which creates a hypothetical topic/post. Afterwards, Embeddings is done on that post and then it searches your site for similar matches to the search query. Finally, it uses Reciprocal Rank Fusion (RFF) to re-rank the top results in line with regular search.
I see an option for AI from quick search?
- The AI quick search option performs AI search faster by skipping creating the hypothetical post. Sometimes this option is faster and provides more relevant results, other times it falls short.
How is topic/post data processed?
- LLM data is processed by a 3rd party provider, please refer to your specific provider for more details. By default, the Embeddings microservice is ran alongside other servers that host your existing forums. There is no third party involved here, and that specific information never leaves your internal network in our virtual private datacenter.
Where does the data go?
- A hypothetical topic/post created by the LLM provider is temporarily cached alongside the Embeddings for that document. Embeddings data is stored in the same database where we store your topics, posts and users, It’s another data table in there.
What does the Embeddings “semantic model” look like? How was it “trained”, and is there a way to test that it can accurately apply to the topics on our “specialized” communities?
- By default we use pre-trained open source models, such as this one. We have deployed to many customers, and found that it performs well for both niche and general communities. If the performance isn’t good enough for your use case, we have more complex models ready to go, but in our experience, the default option is a solid choice.
Last edited by @Saif 2024-11-04T17:58:20Z
Last checked by @hugh 2024-08-06T04:44:33Z
Check document
Perform check on document: