On very large sites, the rare cache misses for Related Topics can take around 200ms, which affects our p99 metric on the topic page. In order to mitigate this impact, we now have several tools at our disposal.
First, one is to migrate the index embedding type from halfvec to bit and change the related topic query to leverage the new bit index by changing the search algorithm from inner product to Hamming distance. This will reduce our index sizes by 90%, severely reducing the impact of embeddings on our storage. By making the related query a bit smarter, we can have zero impact on recall by using the index to over-capture N*2 results, then re-ordering those N*2 using the full halfvec vectors and taking the top N. The expected impact is to go from 200ms to <20ms for cache misses and from a 2.5GB index to a 250MB index on a large site.
Another tool is migrating our index type from IVFFLAT to HNSW, which can increase the cache misses performance even further, eventually putting us in the under 5ms territory.
Co-authored-by: Roman Rizzi <roman@discourse.org>
Polymorphic RAG means that we will be able to access RAG fragments both from AiPersona and AiCustomTool
In turn this gives us support for richer RAG implementations.
* FIX: we were never reindexing old content
Embedding backfill contains logic for searching for old content
change and then backfilling.
Unfortunately it was excluding all topics that had embedding
unconditionally, leading to no backfill ever happening.
This change adds a test and ensures we backfill.
* over select results, this ensures we will be more likely to find
ai results when filtered
This allows callers of embedding based search to bypass hyde.
Hyde will expand the search term using an LLM, but if an LLM is
performing the search we can skip this expansion.
It also introduced some tests for the controller which we did not have
- Introduce new support for GPT4o (automation / bot / summary / helper)
- Properly account for token counts on OpenAI models
- Track feature that was used when generating AI completions
- Remove custom llm support for summarization as we need better interfaces to control registration and de-registration
BAAI/bge-m3 is an interesting model, that is multilingual and with a
context size of 8192. Even with a 16x larger context, it's only 4x slower
to compute it's embeddings on the worst case scenario.
Also includes a minor refactor of the rake task, including setting model
and concurrency levels when running the backfill task.
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
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>
1. on failure we were queuing a job to generate embeddings, it had the wrong params. This is both fixed and covered in a test.
2. backfill embedding in the order of bumped_at, so newest content is embedded first, cover with a test
3. add a safeguard for hidden site setting that only allows batches of 50k in an embedding job run
Previously old embeddings were updated in a random order, this changes it so we update in a consistent order
* FEATURE: add support for new OpenAI embedding models
This adds support for just released text_embedding_3_small and large
Note, we have not yet implemented truncation support which is a
new API feature. (triggered using dimensions)
* Tiny side fix, recalc bots when ai is enabled or disabled
* FIX: downsample to 2000 items per vector which is a pgvector limitation
* REFACTOR: Represent generic prompts with an Object.
* Adds a bit more validation for clarity
* Rewrite bot title prompt and fix quirk handling
---------
Co-authored-by: Sam Saffron <sam.saffron@gmail.com>
Fixes a regression from 140359c which caused we to set this globally based on post count, rendering the cost of an index scan on the topics table too high and making the planner, correctly, not use the index anymore.
Hopefully https://github.com/pgvector/pgvector/issues/235 lands soon.
Followup 2636efcd1b,
whenever ruby code was changed locally this would break
module loading, giving an "uninitialized constant
DiscourseAi::Embeddings::EntryPoint::SemanticRelated" error.
This allows admins to configure services with multiple backends using DNS SRV records. This PR also adds support for shared secret auth via headers for TEI and vLLM endpoints, so they are inline with the other ones.
* FIX: AI helper not working correctly with mixtral
This PR introduces a new function on the generic llm called #generate
This will replace the implementation of completion!
#generate introduces a new way to pass temperature, max_tokens and stop_sequences
Then LLM implementers need to implement #normalize_model_params to
ensure the generic names match the LLM specific endpoint
This also adds temperature and stop_sequences to completion_prompts
this allows for much more robust completion prompts
* port everything over to #generate
* Fix translation
- On anthropic this no longer throws random "This is your translation:"
- On mixtral this actually works
* fix markdown table generation as well
Previous to this change we relied on explicit loading for a files in Discourse AI.
This had a few downsides:
- Busywork whenever you add a file (an extra require relative)
- We were not keeping to conventions internally ... some places were OpenAI others are OpenAi
- Autoloader did not work which lead to lots of full application broken reloads when developing.
This moves all of DiscourseAI into a Zeitwerk compatible structure.
It also leaves some minimal amount of manual loading (automation - which is loading into an existing namespace that may or may not be there)
To avoid needing /lib/discourse_ai/... we mount a namespace thus we are able to keep /lib pointed at ::DiscourseAi
Various files were renamed to get around zeitwerk rules and minimize usage of custom inflections
Though we can get custom inflections to work it is not worth it, will require a Discourse core patch which means we create a hard dependency.
Rafael dos Santos Silva
Mark VanLandingham
Sam
Loïc Guitaut
Bianca Nenciu
Roman Rizzi
Keegan George
Martin Brennan