Commit Graph

874 Commits

Author SHA1 Message Date
Rafael dos Santos Silva 525be42aa5
FIX: AIHelper custom prompts with OpenAI had wrong type (#230) 2023-09-25 17:26:00 -03:00
Keegan George 2e5a39360a
FEATURE: Create custom prompts with composer AI helper (#214)
* DEV: Add icon support

* DEV: Add basic setup for custom prompt menu

* FEATURE: custom prompt backend

* fix custom prompt param check

* fix custom prompt replace

* WIP

* fix custom prompt usage

* fixes

* DEV: Update front-end

* DEV: No more custom prompt state

* DEV: Add specs

* FIX: Title/Category/Tag suggestions

Suggestion dropdowns broke because it `messages_with_user_input(user_input)` expects a hash now.

* DEV: Apply syntax tree

* DEV: Restrict custom prompts to configured groups

* oops

* fix tests

* lint

* I love tests

* lint is cool tho

---------

Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
2023-09-25 15:12:54 -03:00
Sam 316ea9624e
FIX: properly truncate !command prompts (#227)
* FIX: properly truncate !command prompts

### What is going on here?

Previous to this change where a command was issued by the LLM it
could hallucinate a continuation eg:

```
This is what tags are

!tags

some nonsense here
```

This change introduces safeguards so `some nonsense here` does not
creep in to the prompt history, poisoning the llm results

This in effect grounds the llm a lot better and results in the llm
forgetting less about results.

The change only impacts Claude at the moment, but will also improve
stuff for llama 2 in future.

Also, this makes it significantly easier to test the bot framework
without an llm cause we avoid a whole bunch of complex stubbing

* blank is not a valid bot response, do not inject into prompt
2023-09-15 07:02:37 +10:00
Roman Rizzi f57c1bb0f6
FEATURE: AI Helper endpoint to generate a thumbnail from text. (#224)
We pass the text to the current LLM and ask them to generate a StableDifussion prompt.
We'll use that to generate 4 samples, temporarily creating uploads and returning their short URLs.
2023-09-14 12:53:44 -03:00
Jarek Radosz 1eb70c4f0a
DEV: Fix rspec-expectations warnings (#228) 2023-09-14 17:50:13 +02:00
Sam 9e94457154
FIX: Made bot more robust (#226)
* FIX: Made bot more robust

This is a collection of small fixes

- Display "Searching for: ..." while searching instead of showing found 0 results.
- Only allow 5 commands in lang chain - 6 feels like too much
- On the 5th command stop informing the engine about functions, so it is forced to complete
- Add another 30 tokens of buffer and explain why
- Typo in command prompt


Co-authored-by: Alan Guo Xiang Tan <gxtan1990@gmail.com>
2023-09-14 16:46:56 +10:00
Keegan George d35c8d5eca
FIX: Conditionally render AI suggestion buttons (#225) 2023-09-13 14:18:48 -07:00
Keegan George cf6a6ed9b8
FIX: AI Helper UX bugs (#223) 2023-09-13 09:53:19 -07:00
Sam cdd6faa648
FEATURE: add filter support to ai bot semantic search (#222)
Previously we would bypass semantic search if any filters were
present

Also shows progress now.
2023-09-13 14:59:45 +10:00
Rafael dos Santos Silva d1642533fb
FIX: Use "Related Topics" label consistently (#221) 2023-09-12 16:23:24 -03:00
Rafael dos Santos Silva 2c87bb0d99
FEATURE: Respect search filters in semantic search (#220)
* FEATURE: Respect search filters in semantic search

* lint
2023-09-12 16:16:33 -03:00
Roman Rizzi 50d7289623
FIX: Trigger initial semantic search. (#219)
I thought this wasn't neccessary and we could safely rely on the appEvent during the initial search.
It only fires if #searchEnabled is true, meaning the search term is valid.
2023-09-12 10:28:07 -03:00
Discourse Translator Bot 0d761f4305
Update translations (#218) 2023-09-12 15:27:58 +02:00
Sam d75e3ca82b
FEATURE: include tag and category context in search (#217)
Previous to this we just included title/body.. tags and category
structure can be very critical for decision making.
2023-09-12 16:09:28 +10:00
Sam b0310f90d3
FEATURE: add tags and categories to read context (#215)
Note, we perform permission checks on tag list against anon
to ensure we do not disclose information about private tags
to the llm which could get extracted.
2023-09-12 11:06:55 +10:00
Roman Rizzi 156931e1f4
FIX: Perform semantic search only when searchTerm is valid (#216) 2023-09-11 11:32:05 -03:00
Keegan George 6295b16678
FEATURE: Add cancel button to loading context menu (#213) 2023-09-07 13:50:56 -07:00
Keegan George 087be9f4da
UX: Prevent input text from covering suggestion button (#212) 2023-09-07 11:52:00 -07:00
Roman Rizzi 0828254d61
FIX: Generate embeddings job was broken (#211)
* FIX: Use correct methods to generate embeddings

* FIX: Generate embeddings job was broken
2023-09-07 11:54:43 -03:00
Sam 615eb8b440
FEATURE: add semantic search with hyde bot (#210)
In specific scenarios (no special filters or limits) we will also
always include 5 semantic results (at least) with every query.

This effectively means that all very wide queries will always return
20 results, regardless of how complex they are.

Also: 

FIX: embedding backfill rake task not working
We renamed internals, this corrects the implementation
2023-09-07 13:25:26 +10:00
Keegan George abe96d5533
DEV: Strip out old modal based AI helper (#209) 2023-09-06 13:28:47 -07:00
Keegan George 0733ff7e67
UX: Show suggestion buttons only if sufficient content is present (#204) 2023-09-06 12:20:08 -07:00
Keegan George 8d674c451a
FIX: Flaky spec in AI Helper modal (#208) 2023-09-06 10:15:11 -07:00
Keegan George aa08f2d2a0
FIX: Flaky Spec (#207) 2023-09-06 09:46:03 -07:00
Rafael dos Santos Silva 5c50d2aa09
FEATURE: Use stop_sequences for faster HyDE searches with Claude (#203) 2023-09-06 10:06:31 -03:00
Roman Rizzi 13d63f1f30
FIX: filter allowed categories from semantic search results (#206) 2023-09-06 10:00:20 -03:00
Alan Guo Xiang Tan 920d4d8c0c
DEV: Skip broken test on CI (#205) 2023-09-06 09:33:43 +08:00
Roman Rizzi 4d854e9232
FIX: Invalidate semantic search cache entries when hyde or embedding model changes (#202) 2023-09-05 18:39:39 -03:00
Keegan George 3a00c38fc5
UX: Change AI Helper toggle icon to sparkles (#201) 2023-09-05 13:21:05 -07:00
Rafael dos Santos Silva 4b42c09814
FEATURE: Tweak HyDE prompts for better grounding in forum subject and limit response size (#200)
* FEATURE: Tweak HyDE prompts for better grounding in forum subject and limit response size

* fix test

* lint
2023-09-05 16:11:07 -03:00
Roman Rizzi 175def1267
FIX: Update migrations with latest vector rep changes (#199) 2023-09-05 14:31:04 -03:00
Rafael dos Santos Silva ee734a340a
FIX: Tag/category suggestion broke in 2c0f535 (#198) 2023-09-05 14:15:01 -03:00
Keegan George ae0238c616
FIX: Flaky spec (#197) 2023-09-05 09:56:12 -07:00
Rafael dos Santos Silva 2c0f535bab
FEATURE: HyDE-powered semantic search. (#136)
* FEATURE: HyDE-powered semantic search.

It relies on the new outlet added on discourse/discourse#23390 to display semantic search results in an unobtrusive way.

We'll use a HyDE-backed approach for semantic search, which consists on generating an hypothetical document from a given keywords, which gets transformed into a vector and used in a asymmetric similarity topic search.

This PR also reorganizes the internals to have less moving parts, maintaining one hierarchy of DAOish classes for vector-related operations like transformations and querying.

Completions and vectors created by HyDE will remain cached on Redis for now, but we could later use Postgres instead.

* Missing translation and rate limiting

---------

Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2023-09-05 11:08:23 -03:00
Discourse Translator Bot 3d83d062a1
Update translations (#186) 2023-09-05 15:42:46 +02:00
Sam 38af2ca63e
FIX: cut completion short after function call is found (#182)
Previous to this change we would keep completing and throw away
result
2023-09-05 10:37:58 +10:00
Rafael dos Santos Silva 86591cf1d2
CHORE: Update Readme (#185) 2023-09-04 15:46:35 -03:00
Rafael dos Santos Silva 4864978495
FEATURE: Return only applicable suggestions in AiHelper category/tags suggestions (#184) 2023-09-04 14:30:33 -03:00
Rafael dos Santos Silva 3c4a53b2cb
FEATURE: Better link in Claude summaries (#183)
* FEATURE: Better link in Claude summaries

* lint
2023-09-04 12:04:47 -03:00
Sam e3abbd9f46
FEATURE: add researcher persona (#181)
The researcher persona has access to Google and can perform
various internet research tasks. At the moment it can not read
web pages, but that is under consideration
2023-09-04 12:05:27 +10:00
Sam 3f9973586e
FIX: ai_bot_allowed_groups now works with restricted visibility (#180)
Previous to this change we relied on client side settings to
determine if an end user has access to the ai bot.

This meant that if a user was not aware they are a member of a
group (as it is with restricted visibility ones) they would not
see the bot button.

All checking has now moved to the server side, and tests were
added to cover.
2023-09-04 11:52:44 +10:00
Rafael dos Santos Silva 43e485cbd9
FEATURE: Additional AI suggestion options (#176) 2023-09-01 17:10:58 -07:00
Sam 181113159b
FIX: setting explorer was exceeding token budget
This refactor changes it so we only include minimal data in the
system prompt which leaves us lots of tokens for specific searches

The new search command allows us to pull in settings on demand

Descriptions are include in short search results, and names only
in longer results

Also: 

* In dev it is important to tell when calls are made to open ai
this adds a console log to increase awareness around token usage

* PERF: stop counting tokens so often

This changes it so we only count tokens once per response

Previously each time we heard back from open ai we would count
tokens, leading to uneeded delays

* bug fix, commands may reach in for tokenizer

* add logging to console for anthropic calls as well

* Update lib/shared/inference/openai_completions.rb

Co-authored-by: Martin Brennan <mjrbrennan@gmail.com>
2023-09-01 11:48:51 +10:00
Loïc Guitaut 65091690eb DEV: Don’t use `Chat::MessageCreator` in specs
As message creation is being rewritten in
https://github.com/discourse/discourse/pull/22390, a new way of using
the underlying service to create chat messages has been implemented in
https://github.com/discourse/discourse/pull/23222.

This patch uses the new fabricator option which will prevent breaking
specs from this plugin when the main PR will be merged.
2023-08-31 11:30:07 +02:00
Sam 00d69b463e
FEATURE: new site setting explorer persona (#178)
Also adds ai_bot_enabled_personas so admins can tweak which stock
personas are enabled.

The new persona has a full listing of all site settings and is
able to get context for each setting.

This means you can ask it to search through settings for something
relevant.

Security wise there is no access to actual configuration of settings
just to the names / description and implementation.

Previously this was part of the forum helper persona however it
just clashes too much with other behaviors, isolating it makes
it far more powerful.

* sneaking this one in, user_emails is a non obvious table in our
structure.

usually one would assume users has emails so the clarifies a bit
better. plus it is a very common table to hit.
2023-08-31 17:02:03 +10:00
Sam 8e4347acba
DEV: rename ai_helper_add_ai_pm_to_header -> ai_bot_add_to_header (#177)
Old name was very unclear, this setting is only used for the bot
so now it follows the same convention others do
2023-08-31 14:42:28 +10:00
Sam db19e37748
FEATURE: add initial support for personas (#172)
This splits out a bunch of code that used to live inside bots
into a dedicated concept called a Persona.

This allows us to start playing with multiple personas for the bot

Ships with:

artist - for making images
sql helper - for helping with data explorer
general - for everything and anything
 
Also includes a few fixes that make the generic LLM function implementation  more robust
2023-08-30 16:15:03 +10:00
Rafael dos Santos Silva 6d69fb479e
DEV: Hide old embeddings pg setting (#169)
* DEV: Hide old embeddings pg setting

* fix yaml
2023-08-29 17:39:21 -03:00
Keegan George 4da4b5609f
FIX: Show warning when trying to generate suggestions without content (#175) 2023-08-29 11:58:45 -07:00
Keegan George 494964c51d
DEV: Dynamically set popper placement (#174) 2023-08-29 11:19:25 -07:00