Commit Graph

993 Commits

Author SHA1 Message Date
jbrw c479b177a7
DEV: Check for presence of currentRoute.attributes (#870) 2024-10-25 13:30:29 -04:00
Rafael dos Santos Silva 8ded4b2e58
FIX: Use present? instead of invalid exists? (#869) 2024-10-25 13:04:42 -03:00
Roman Rizzi a2b1ea3c63
FEATURE: Fast-track gist regeneration when a hot topic gets a new post (#860)
* FEATURE: Fast-track gist regeneration when a hot topic gets a new post

* DEV: Introduce an upsert-like summarize

* FIX: Only enqueue fast-track gist for hot hot hot topics

---------

Co-authored-by: Rafael Silva <xfalcox@gmail.com>
2024-10-25 12:38:49 -03:00
Rafael dos Santos Silva 33da27e231
FIX: Change hot gist prompt to avoid title repeating #859 (#859)
Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2024-10-25 12:12:33 -03:00
Roman Rizzi ec97996905
FIX/REFACTOR: FoldContent revamp (#866)
* FIX/REFACTOR: FoldContent revamp

We hit a snag with our hot topic gist strategy: the regex we used to split the content didn't work, so we cannot send the original post separately. This was important for letting the model focus on what's new in the topic.

The algorithm doesn’t give us full control over how prompts are written, and figuring out how to format the content isn't straightforward. This means we're having to use more complicated workarounds, like regex.

To tackle this, I'm suggesting we simplify the approach a bit. Let's focus on summarizing as much as we can upfront, then gradually add new content until there's nothing left to summarize.

Also, the "extend" part is mostly for models with small context windows, which shouldn't pose a problem 99% of the time with the content volume we're dealing with.

* Fix fold docs

* Use #shift instead of #pop to get the first elem, not the last
2024-10-25 11:51:17 -03:00
Sam 12869f2146
FIX: testing tool was not showing rag results (#867)
This changeset contains 4 fixes:

1. We were allowing running tests on unsaved tools,
this is problematic cause uploads are not yet associated or indexed
leading to confusing results. We now only show the test button when
tool is saved.


2. We were not properly scoping rag document fragements, this
meant that personas and ai tools could get results from other
unrelated tools, just to be filtered out later


3. index.search showed options as "optional" but implementation
required the second option

4. When testing tools searching through document fragments was
not working at all cause we did not properly load the tool
2024-10-25 16:01:25 +11:00
Sam 4923837165
FIX: Llm selector / forced tools / search tool (#862)
* FIX: Llm selector / forced tools / search tool


This fixes a few issues:

1. When search was not finding any semantic results we would break the tool
2. Gemin / Anthropic models did not implement forced tools previously despite it being an API option
3. Mechanics around displaying llm selector were not right. If you disabled LLM selector server side persona PM did not work correctly.
4. Disabling native tools for anthropic model moved out of a site setting. This deliberately does not migrate cause this feature is really rare to need now, people who had it set probably did not need it.
5. Updates anthropic model names to latest release

* linting

* fix a couple of tests I missed

* clean up conditional
2024-10-25 06:24:53 +11:00
Rafael dos Santos Silva 3022d34613
FEATURE: Support srv records for OpenAI compatible LLMs (#865) 2024-10-24 15:47:12 -03:00
David Taylor c1fa84ad29
DEV: Update form-template-field/upload uppy usage (#863) 2024-10-24 15:21:13 +01:00
Kris fc6f0a6560
UX: minor gist optimizations for readability (#864) 2024-10-24 09:31:52 -04:00
Keegan George 9e8608b070
UX: Hide AI bot in seeded LLM (#858)
AI bot won't be turned on for seeded LLMs so it makes no sense to expose it here. This will cleanup the template and avoid the double `{{#unless}}` check.
2024-10-23 16:36:17 -07:00
Kris 72111a10ae
UX: add disclosure for topic list gists (#861) 2024-10-23 19:32:22 -04:00
Rafael dos Santos Silva 96f5f8cbd0
FIX: Basic cleanup of AI Caption to remove line breaks and pipes (#857) 2024-10-23 18:38:29 -03:00
Keegan George 9af0c2e719
UX: Improve seeded LLM edit page (#856) 2024-10-23 13:58:27 -07:00
Kris 0aa2789437
UX: switch gist outlet to avoid badges (#855) 2024-10-23 15:10:41 -04:00
Kris 657d103919
UX: adjust gist position, darken unread color (#854) 2024-10-23 13:00:52 -04:00
Sam f1283e156d
FEATURE: allow scoping of google tool queries (#852)
This allows to simply scope search results to specific domains and prepend arbitrary snippets to searches made
2024-10-23 16:55:10 +11:00
Sam 059d3b6fd2
FEATURE: better logging for automation reports (#853)
A new feature_context json column was added to ai_api_audit_logs

This allows us to store rich json like context on any LLM request
made.

This new field now stores automation id and name.

Additionally allows llm_triage to specify maximum number of tokens

This means that you can limit the cost of llm triage by scanning only
first N tokens of a post.
2024-10-23 16:49:56 +11:00
Keegan George eae7716177
DEV: Improve `ai-streamer` API (#851)
In preparation for applying the streaming animation elsewhere, we want to better improve the organization of folder structure and methods used in the `ai-streamer`
2024-10-22 10:55:35 -07:00
Discourse Translator Bot b604ff9a23
Update translations (#850) 2024-10-22 22:44:42 +09:00
Sam c6276be63e
FIX: add missing translation (#849) 2024-10-22 12:10:08 +11:00
Sam a1f859a415
FEATURE: improve visibility of AI usage in LLM page (#845)
This changeset: 

1. Corrects some issues with "force_default_llm" not applying
2. Expands the LLM list page to show LLM usage
3. Clarifies better what "enabling a bot" on an llm means (you get it in the selector)
2024-10-22 11:16:02 +11:00
Keegan George 712a07c39b
DEV: `IMAGE_MARKDOWN_REGEX` import available in core (#847) 2024-10-21 14:48:10 -07:00
Roman Rizzi 3533814870
UX: Avoid introductory phrases and summarize topics without replies (#848) 2024-10-21 17:53:48 -03:00
Roman Rizzi 6d504ab80d
FEATURE: Make hot topic gists opt-in. (#846)
This change restricts gists to members of specific groups. It also fixes a bug where other lists could display the gist if available.
2024-10-21 15:15:25 -03:00
Keegan George 37c2930fbf
FIX: Decouple DOM manipulation from SummaryStreamer (#844)
Previously, when we added smooth streaming animation to summarization (https://github.com/discourse/discourse-ai/pull/778) we used the same logic and lib we did for AI Bot. However, since `AiSummaryBox` is an Ember component, the direct DOM manipulation done in the streamer (`SummaryUpdater`) would often result in issues with summarization where sometimes summarization updates would hang, especially on the last result. This is likely due to the DOM manipulation being done in the streamer being incongruent with Ember's way of rendering.

In this PR, we remove the direct DOM manipulation done in the lib `SummaryUpdater` in favour of directly updating the properties in `AiSummaryBox` using the `componentContext`. Instead of messing with Ember's rendered DOM, passing the updates and allowing the component to render the updates directly should likely prevent further issues with summarization.

The bug itself is quite difficult to repro and also difficult to test, so no tests have been added to this PR. But I will be manually testing and assessing for any potential issues.
2024-10-21 09:15:25 -07:00
Roman Rizzi e768fa877e
FIX: Don't regenerate up to date gists (#843) 2024-10-18 18:49:01 -03:00
Roman Rizzi 27b5542357
FEATURE: Generate topic gists for the hot topics list. (#837)
* Display gists in the hot topics list

* Adjust hot topics gist strategy and add a job to generate gists

* Replace setting with a configurable batch size

* Avoid loading summaries for other topic lists

* Tweak gist prompt to focus on latest posts in the context of the OP

* Remove serializer hack and rely on core change from discourse/discourse#29291

* Update lib/summarization/strategies/hot_topic_gists.rb

Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>

---------

Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
2024-10-18 18:01:39 -03:00
Rafael dos Santos Silva decf1bb49d
FIX: api key header error (#839)
* FIX: api key header error

* FIX: remove unnecessary headers

* FIX: a error

* FEATURE: Add both headers

---------

Co-authored-by: 耗子 <i@haozi.net>
2024-10-16 15:57:36 -03:00
Kris 25cc03809a
DEV: ensure far-copy icon is included in subset (#841) 2024-10-16 12:32:13 -04:00
Loïc Guitaut 7919173cba DEV: Use `ChatSDK.create` instead of service in specs
This patch will allow upcoming changes to services
(https://github.com/discourse/discourse/pull/29129) without breaking the
`discourse-ai` specs.
2024-10-16 18:18:32 +02:00
Rafael dos Santos Silva 792703c942
FEATURE: Discord Bot integration (#831)
This adds support for the a Discord bot that can search in a Discourse instance when invoked via slash commands in Discord Guild channel.
2024-10-16 12:41:18 -03:00
Discourse Translator Bot 3432f6654f
Update translations (#836) 2024-10-16 17:52:11 +09:00
Martin Brennan d7745d1ac3
FIX: Remove missed AiPersona.allowed_chat (#838)
Followup bdf3b6268b

I think this is the fix but not sure how to test it,
this is breaking the build
2024-10-16 10:33:24 +11:00
Sam bdf3b6268b
FEATURE: smarter persona tethering (#832)
Splits persona permissions so you can allow a persona on:

- chat dms
- personal messages
- topic mentions
- chat channels

(any combination is allowed)

Previously we did not have this flexibility.

Additionally, adds the ability to "tether" a language model to a persona so it will always be used by the persona. This allows people to use a cheaper language model for one group of people and more expensive one for other people
2024-10-16 07:20:31 +11:00
Roman Rizzi c7acb4a6a0
REFACTOR: Support of different summarization targets/prompts. (#835)
* DEV: Add summary types

* Refactor for different summary types

* Use enum for summary types

* Update lib/summarization/strategies/topic_summary.rb

Co-authored-by: Penar Musaraj <pmusaraj@gmail.com>

* Update lib/summarization/strategies/topic_gist.rb

Co-authored-by: Penar Musaraj <pmusaraj@gmail.com>

* Update lib/summarization/strategies/chat_messages.rb

Co-authored-by: Penar Musaraj <pmusaraj@gmail.com>

* Fix chat_messages single prompt

* Small tweak to the chat summarization prompt

---------

Co-authored-by: Penar Musaraj <pmusaraj@gmail.com>
2024-10-15 13:53:26 -03:00
Rafael dos Santos Silva 791fad1e6a
FEATURE: Index embeddings using bit vectors (#824)
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>
2024-10-14 13:26:03 -03:00
Kelv 6615104389
DEV: Switch to use pnpm (#833) 2024-10-14 13:37:20 +02:00
Hoa Nguyen 94010a5f78
FEATURE: Tools for models from Ollama provider (#819)
Adds support for Ollama function calling
2024-10-11 07:25:53 +11:00
Sam 6c4c96e83c
FEATURE: allow persona to only force tool calls on limited replies (#827)
This introduces another configuration that allows operators to
limit the amount of interactions with forced tool usage.

Forced tools are very handy in initial llm interactions, but as
conversation progresses they can hinder by slowing down stuff
and adding confusion.
2024-10-11 07:23:42 +11:00
Mark VanLandingham 52d90cf1bc
DEV: Add apply_modifier for SemanticTopicQuery topics list (#830) 2024-10-10 12:13:16 -05:00
Bianca Nenciu c5b323fc07
DEV: Fix mismatched column types in tests (#826)
The primary key is usually a bigint column, but the foreign key columns
usually are of integer type. This can lead to issues when joining these
columns due to mismatched types and different value ranges.

In a recent core change, all bigint sequences will start at a very high
value in the test environment to surface this type of errors. The same
change also added a temporary API that changes the column type to bigint
in order to allow for the tests to run.

The plugin API is only temporary and it is important for these plugins
to migrate their columns to bigint to avoid issues in the future.
2024-10-10 18:39:36 +03:00
Rafael dos Santos Silva 95e70474fd
DEV: Skip flaky test (#829) 2024-10-10 12:02:31 -03:00
Martin Brennan 4f6b36147b
UX: Remove AdminPageSubheader style override (#828)
In this core commit https://github.com/discourse/discourse/pull/29149 we
are changing the subheader title to H2 and making the size smaller,
this style override is no longer needed.
2024-10-10 17:18:32 +10:00
Mark VanLandingham 51494db236
REVERT: "DEV: Convert related-topics to gjs (#822)" (#825)
This reverts commit a3c6938cb3.
2024-10-09 10:10:03 -05:00
Sam e1a0eb6131
FEATURE: support chain halting and upload creation support (#821)
This adds chain halting (ability to terminate llm chain in a tool)
and the ability to create uploads in a tool

Together this lets us integrate custom image generators into a
custom tool.
2024-10-09 08:17:45 +11:00
Discourse Translator Bot 3170e14acb
Update translations (#823) 2024-10-08 20:21:52 +02:00
Jarek Radosz a3c6938cb3
DEV: Convert related-topics to gjs (#822) 2024-10-08 14:16:08 +02:00
Sam 545500b329
FEATURE: allows forced LLM tool use (#818)
* FEATURE: allows forced LLM tool use

Sometimes we need to force LLMs to use tools, for example in RAG
like use cases we may want to force an unconditional search.

The new framework allows you backend to force tool usage.

Front end commit to follow

* UI for forcing tools now works, but it does not react right

* fix bugs

* fix tests, this is now ready for review
2024-10-05 09:46:57 +10:00
Sam c294b6d394
FEATURE: allow llm triage to automatically hide posts (#820)
Previous to this change we could flag, but there was no way
to hide content and treat the flag as spam.

We had the option to hide topics, but this is not desirable for
a spam reply.

New option allows triage to hide a post if it is a reply, if the
post happens to be the first post on the topic, the topic will
be hidden.
2024-10-04 16:11:30 +10:00