Commit Graph

337 Commits

Author SHA1 Message Date
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
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
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
Rafael dos Santos Silva d1642533fb
FIX: Use "Related Topics" label consistently (#221) 2023-09-12 16:23:24 -03:00
Discourse Translator Bot 0d761f4305
Update translations (#218) 2023-09-12 15:27:58 +02:00
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 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
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 7457feced8
FEATURE: Show suggested title prompt in new location (#171) 2023-08-29 09:45:53 -07:00
Discourse Translator Bot 345bfed19f
Update translations (#173) 2023-08-29 15:51:02 +02:00
Sam b14cb864dc
FEATURE: add setting_context experimental command (#160)
This command can be used to extract information about a discourse
site setting directly from source.

To operate it needs the rg binary in the container.
2023-08-29 10:43:58 +10:00
Rafael dos Santos Silva e673b568d9
FEATURE: StableBeluga2 support for AiHelper (#162)
* FEATURE: StableBeluga2 support for AiHelper

* lint
2023-08-25 15:54:51 -03:00
Keegan George 7790313b1b
DEV: Add review menu state (#159) 2023-08-24 17:49:24 -07:00
Keegan George 6df850d473
FEATURE: AI Helper Context Menu (#148) 2023-08-23 10:35:40 -07:00
Discourse Translator Bot 95881fce74
Update translations (#149) 2023-08-22 14:34:48 -03:00
Roman Rizzi f111bcb35b
FIX: Display related topics when scrolling to the bottom of a topic. (#150)
Besides updating the connector using the new tracking preference service interface, this PR fixes a bug where due to `ai_embeddings_semantic_related_topics_enabled` not having `client: true` the initializer never ran, and we didn't show the related topics list when scrolling to the bottom of a long topic.
2023-08-22 14:10:21 -03:00
Martin Brennan 486a130c25
DEV: Categorize plugin settings into discourse_ai (#144)
Moving the plugin settings into a more specific category
makes them easier to find in the plugin UI and removes
them from the generic "Plugins" tab.
2023-08-21 14:46:34 -03:00
Sam b4477ecdcd
FEATURE: support 16k and 32k variants for Azure GPT (#140)
Azure requires a single HTTP endpoint per type of completion.

The settings: `ai_openai_gpt35_16k_url` and `ai_openai_gpt4_32k_url` can be
used now to configure the extra endpoints

This amends token limit which was off a bit due to function calls and fixes
a minor JS issue where we were not testing for a property
2023-08-17 11:00:11 +10:00
Sam 01f833f86e
FEATURE: optional warning attached to all AI bot conversations (#137)
* FEATURE: optional warning attached to all AI bot conversations

This commit introduces `ai_bot_enable_chat_warning` which can be used
to warn people prior to starting a chat with the bot.

In particular this is useful if moderators are regularly reading chat
transcripts as it sets expectations early.

By default this is disabled.

Also:

- Stops making ajax call prior to opening composer
- Hides PM title when starting a bot PM

Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
2023-08-17 06:29:58 +10:00
Discourse Translator Bot 525c8b0913
Update translations (#135) 2023-08-15 21:25:07 +02:00
Régis Hanol 7077c31ab8
Typo in site setting's description (#132) 2023-08-10 14:07:13 -03:00
Sam 7eedbf29e0
FIX: refine image and read command (#131)
- Attempt to hint reading is done by sending complete:true
- Do not include post_number in result unless it was sent in
- Rush visual feedback when a command is run (ensure we always revise)
- Include hyperlink in read command description
- Stop round tripping to GPT after image generation (speeds up images by a lot)
- Add a test for image command
2023-08-09 16:01:48 +10:00
Sam 958dfc360e
FEATURE: experimental read command for bot (#129)
This command is useful for reading a topics content. It allows us to perform
critical analysis or suggest answers.

Given 8k token limit in GPT-4 I hardcoded reading to 1500 tokens, but we can
follow up and allow larger windows on models that support more tokens.

On local testing even in this limited form this can be very useful.
2023-08-09 07:19:56 +10:00
Discourse Translator Bot b1987f279d
Update translations (#130) 2023-08-08 15:42:39 +02:00
Rafael dos Santos Silva eb7fff3a55
FEATURE: Add support for StableBeluga and Upstage Llama2 instruct (#126)
* FEATURE: Add support for StableBeluga and Upstage Llama2 instruct

This means we support all models in the top3 of the Open LLM Leaderboard

Since some of those models have RoPE, we now have a setting so you can
customize the token limit depending which model you use.
2023-08-03 15:29:30 -03:00
Rafael dos Santos Silva 8b157feea5
FEATURE: Compatibility with protected Hugging Face Endpoints (#123)
* FEATURE: Compatibility with protected Hugging Face Endpoints
2023-08-02 17:00:00 -03:00
Sam 602bb843ea
FEATURE: add support for final stable diffusion xl model (#122) 2023-08-02 16:53:28 -03:00
Discourse Translator Bot c26d48e3b1
Update translations (#119) 2023-08-01 16:05:55 +02:00
Roman Rizzi c8de9495c8
UX: Update related-topics to follow <MoreTopics/> conventions (#118) 2023-07-31 18:33:37 -03:00
Rafael dos Santos Silva 3e7c99de89
FEATURE: Support for locally infered embeddings in 100 languages (#115)
* FEATURE: Support for locally infered embeddings in 100 languages

* add table
2023-07-27 15:50:03 -03:00
Rafael dos Santos Silva b25daed60b
FEATURE: Llama2 for summarization (#116) 2023-07-27 13:55:32 -03:00
Sam 4b0c077ce5
FEATURE: port to use claude-2 for chat bot (#114)
Claude 1 costs the same and is less good than Claude 2. Make use of Claude
2 in all spots ...

This also fixes streaming so it uses the far more efficient streaming protocol.
2023-07-27 11:24:44 +10:00
Discourse Translator Bot 2031388f9c
Update translations (#109) 2023-07-25 17:57:58 +02:00
Rafael dos Santos Silva 5e3f4e1b78
FEATURE: Embeddings to main db (#99)
* FEATURE: Embeddings to main db

This commit moves our embeddings store from an external configurable PostgreSQL
instance back into the main database. This is done to simplify the setup.

There is a migration that will try to import the external embeddings into
the main DB if it is configured and there are rows.

It removes support from embeddings models that aren't all_mpnet_base_v2 or OpenAI
text_embedding_ada_002. However it will now be easier to add new models.

It also now takes into account:
  - topic title
  - topic category
  - topic tags
  - replies (as much as the model allows)

We introduce an interface so we can eventually support multiple strategies
for handling long topics.

This PR severely damages the semantic search performance, but this is a
temporary until we can get adapt HyDE to make semantic search use the same
embeddings we have for semantic related with good performance.

Here we also have some ground work to add post level embeddings, but this
will be added in a future PR.

Please note that this PR will also block Discourse from booting / updating if 
this plugin is installed and the pgvector extension isn't available on the 
PostgreSQL instance Discourse uses.
2023-07-13 12:41:36 -03:00
Rafael dos Santos Silva 9d10a152b9
FEATURE: Claude 2 for summarization and AIHelper (#101) 2023-07-13 12:32:08 -03:00
Sam a028309cbd
FEATURE: add ai_bot_enabled_chat commands and tune search (#94)
* FEATURE: add ai_bot_enabled_chat commands and tune search

This allows admins to disable/enable GPT command integrations.

Also hones search results which were looping cause the result did not denote
the failure properly (it lost context)

* include more context for google command
include more context for time command

* type
2023-06-21 17:10:30 +10:00
Sam d1ab79e82f
FEATURE: Add Azure cognitive service support (#93)
The new site settings:

ai_openai_gpt35_url : distribution for GPT 16k
ai_openai_gpt4_url: distribution for GPT 4
ai_openai_embeddings_url: distribution for ada2

If untouched we will simply use OpenAI endpoints.

Azure requires 1 URL per model, OpenAI allows a single URL to serve multiple models. Hence the new settings.
2023-06-21 10:39:51 +10:00
Sam 30778d8af8
FIX: avoid storing corrupt prompts (#92)
```
prompt << build_message(bot_user.username, reply)
```

Would store a "cooked" prompt which is invalid, instead just store the raw
values which are later passed to build_message

Additionally:

1. Disable summary command which needs honing
2. Stop storing decorations (searched for X) in prompt which leads to straying
3. Ship username directly to model, avoiding "user: content" in prompts. This
 was causing GPT to stray
2023-06-20 15:44:03 +10:00
David Taylor 68bc80e19d
DEV: Fix Zeitwerk reloading error (#89)
Using `.append` can lead to a 'two routes with the same name' error
2023-06-16 11:32:54 +01:00
Roman Rizzi 3364fec425
DEV: Remove the summarization feature (#83)
* DEV: Remove the summarization feature

Instead, we'll register summarization implementations for OpenAI, Anthropic, and Discourse AI using the API defined in discourse/discourse#21813.

Core and chat will implement features on top of these implementations instead of this plugin extending them.

* Register instances that contain the model, requiring less site settings
2023-06-13 14:32:26 -03:00
Sam 92fb84e24d
iterate commands (#73)
* FEATURE: introduce a more efficient formatter

Previous formatting style was space inefficient given JSON consumes lots
of tokens, the new format is now used consistently across commands

Also fixes

- search limited to 10
- search breaking on limit: non existent directive

* Slight improvement to summarizer
Stop blowing up context with custom prompts

* ensure we include the guiding message

* correct spec

* langchain style summarizer ...

much more accurate (albeit more expensive)

* lint
2023-05-22 12:09:14 +10:00
Sam d59ed1091b
FEATURE: add support for GPT <-> Forum integration
This change-set connects GPT based chat with the forum it runs on. Allowing it to perform search, lookup tags and categories and summarize topics. 

The integration is currently restricted to public portions of the forum. 

Changes made:

- Do not run ai reply job for small actions
- Improved composable system prompt
- Trivial summarizer for topics
- Image generator 
- Google command for searching via Google
- Corrected trimming of posts raw (was replacing with numbers) 
- Bypass of problem specs

The feature works best with GPT-4


---------

Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2023-05-20 17:45:54 +10:00
Rafael dos Santos Silva 262ed4753e
FEATURE: Basic StableDiffusion text2img support (#72) 2023-05-20 09:38:08 +10:00
Roman Rizzi 9ae8f86850
UX: Improvements to the AI Bot header shortcut (#66)
- Humanize model names
- Focus composer editor when starting a PM with a bot
- Correctly close the models dropdown when clicking outside
2023-05-17 15:59:48 -03:00
Roman Rizzi 5ade5d7404
UX: Add missing label translation (#64) 2023-05-16 16:56:30 -03:00
Roman Rizzi 362f6167d1
FEATURE: Less friction for starting a conversation with an AI bot. (#63)
* FEATURE: Less friction for starting a conversation with an AI bot.

This PR adds a new header icon as a shortcut to start a conversation with one of our AI Bots. After clicking and selecting one from the dropdown menu, we'll open the composer with some fields already filled (recipients and title).

If you leave the title as is, we'll queue a job after five minutes to update it using a bot suggestion.

* Update assets/javascripts/initializers/ai-bot-replies.js

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

* Update assets/javascripts/initializers/ai-bot-replies.js

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

---------

Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
2023-05-16 14:38:21 -03:00
Rafael dos Santos Silva 3c9513e754
Refinements to embeddings and tokenizers (#61)
* Refinements to embeddings and tokenizers

* lint

* Truncate with tokenizers for summary

* fix
2023-05-15 15:10:42 -03:00
Sam 93d9d9ea91
FEATURE: hide various api keys in site settings (#59)
Also... ensures that plugin has a link to more info and proper description
2023-05-12 12:54:25 +10:00
Rafael dos Santos Silva 97124b30de
FEATURE: Update summarization token count and add Claude 100k (#58) 2023-05-11 15:35:58 -03:00
Roman Rizzi 7e3cb0ea16
FEATURE: Multi-model support for the AI Bot module. (#56)
We'll create one bot user for each available model. When listed in the `ai_bot_enabled_chat_bots` setting, they will reply.

This PR lets us use Claude-v1 in stream mode.
2023-05-11 10:03:03 -03:00
Rafael dos Santos Silva e5537d4c77
FEATURE: Allow excluding closed topics from semantic related (#55) 2023-05-09 15:30:50 -03:00
Roman Rizzi 71b105a1bb
FEATURE: Introduce the ai-bot module (#52)
This module lets you chat with our GPT bot inside a PM. The bot only replies to members of the groups listed on the ai_bot_allowed_groups setting and only if you invite it to participate in the PM.
2023-05-05 15:28:31 -03:00
Rafael dos Santos Silva 29b22243de
FIX: Toxicity automatic flagging should be disabled by default (#51) 2023-05-03 16:44:33 -03:00
Roman Rizzi 38e007a3a5
FEATURE: Topic summarization (#41)
* FEATURE: Topic summarization

Summarize topics using the TopicView's "summary" filter. The UI is similar to what we do for chat, but we don't allow the user to select a timeframe.


Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
2023-04-19 17:57:31 -03:00
Rafael dos Santos Silva bb0b829634
FEATURE: Anthropic Claude for AIHelper and Summarization modules (#39) 2023-04-10 11:04:42 -03:00
Roman Rizzi f2e52f7f24
FIX: Check for chat channel permissions (#38) 2023-04-06 09:07:31 -03:00
Rafael dos Santos Silva 5549e4d5b3
FEATURE: Chat channel summarization. (#32)
* start summary module

* chat channel summarization

* FEATURE: modal for channel summarization

---------

Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2023-04-04 11:24:09 -03:00
Roman Rizzi 333cb8f212
FIX: Don't try to use pg headlines for semantic search. (#36)
Depends on discourse/discourse#20939.
2023-04-03 11:48:38 -03:00
Roman Rizzi 4e05763a99
FEATURE: Semantic assymetric full-page search (#34)
Depends on discourse/discourse#20915

Hooks to the full-page-search component using an experimental API and performs an assymetric similarity search using our embeddings database.
2023-03-31 15:29:56 -03:00
Rafael dos Santos Silva 99886fb64d
Update default thresholds for Toxicity (#33) 2023-03-31 13:03:44 -03:00
Sam 0d80d9ec49
FEATURE: allow limiting results in related topics section (#30)
Also:

- Normalizes behavior between logged in and anon,
 we only show related topics in the related topic section

- Renames "suggested" to "related" given this only exists in related section
- Adds a spec section to ensure anon does not regress
- Adds `ai_embeddings_semantic_related_topics` to limit related topics

Renamed settings:

ai_embeddings_semantic_suggested_model -> ai_embeddings_semantic_related_model
ai_embeddings_semantic_suggested_topics_enabled -> ai_embeddings_semantic_related_topics_enabled

Plugins is still in an experimental phase and not much is overidden hence
avoiding adding site setting migrations.


Co-authored-by: Krzysztof Kotlarek <kotlarek.krzysztof@gmail.com>
2023-03-31 11:04:34 +11:00
Sam 1d097b9d82
FEATURE: attempt to include related topics above suggested (#28)
Allows related topics to show up for logged on users

- Introduces a new "Related Topics" block above suggested when related topics exist
- Renames `ai_embeddings_semantic_suggested_topics_anons_enabled` -> `ai_embeddings_semantic_suggested_topics_enabled` (given it is only deployed on 1 site not bothering with a migration)
- Adds an integration test to ensure data arrives correctly on the client
2023-03-31 09:07:22 +11:00
Rafael dos Santos Silva b942a18298
FEATURE: Support for GPT-4 in AI Helper module (#29) 2023-03-28 23:22:34 -03:00
Roman Rizzi 4c960970fa
DEV: Log information about errors from the completions OpenAI API (#26) 2023-03-22 16:00:28 -03:00
Sam 1d14f7ffaf
FEATURE: Add a markdown table AI helper (#25) 2023-03-22 13:16:29 -03:00
Roman Rizzi 39f7f1f29e
FEATURE: Prompts can consist of multiple messages. (#21)
A prompt with multiple messages leads to better results, as the AI can learn for given examples. Alongside this change, we provide a better default proofreading prompt.
2023-03-21 12:04:59 -03:00
Roman Rizzi 95d7692ae8
FIX: Fix reviewable title translations (#18) 2023-03-20 10:09:20 -03:00
Roman Rizzi 320ac6e84b
REFACTOR: Store prompts in a dedicated table. (#14)
This change makes it easier to add new prompts to our AI helper. We don't have a UI for it yet. You'll have to do it through a console.
2023-03-17 15:14:19 -03:00
Rafael dos Santos Silva 80d662e9e8
FEATURE: Semantic Suggested Topics (#10) 2023-03-15 17:21:45 -03:00
Roman Rizzi f99fe7e1ed
FEATURE: Composer AI helper (#8)
* FEATURE: Composer AI helper

This change introduces a new composer button for the group members listed in the `ai_helper_allowed_groups` site setting.

Users can use chatGPT to review, improve, or translate their posts to English.

* Add a safeguard for PMs and don't rely on parentView
2023-03-15 17:02:20 -03:00
Rafael dos Santos Silva 510c6487e3
DEV: Preparation work for multiple inference providers (#5) 2023-03-07 16:14:39 -03:00
Roman Rizzi a838116cd5
FEATURE: Use dedicated reviewables for AI flags. (#4)
This change adds two new reviewable types: ReviewableAIPost and ReviewableAIChatMessage. They have the same actions as their existing counterparts: ReviewableFlaggedPost and ReviewableChatMessage.

We'll display the model used and their accuracy when showing these flags in the review queue and adjust the latter after staff performs an action, tracking a global accuracy per existing model in a separate table.


* FEATURE: Dedicated reviewables for AI flags

* Store and adjust model accuracy

* Display accuracy in reviewable templates
2023-03-07 15:39:28 -03:00
Rafael dos Santos Silva a5f1b003d9
Set default endpoints for all modules so plugins works out of the box (#2) 2023-02-27 16:44:11 -03:00
Roman Rizzi 94933f3c58
DEV: Add missing specs for the toxicity module 2023-02-24 07:53:43 -03:00
Roman Rizzi e8bffcdd64
DEV: Add tests for the sentiment module 2023-02-23 15:50:10 -03:00
Rafael dos Santos Silva a73931c151
Refactoring of nsfw and flagger 2023-02-23 12:13:26 -03:00
Roman Rizzi 6f0c141062
FEATURE: Introduce NSFW content detection basic flow. 2023-02-23 11:08:34 -03:00
Rafael dos Santos Silva 6cf411ec90
add toxicity and sentiment modules 2023-02-22 20:46:53 -03:00
Roman Rizzi 2b319d9077
Initial commit 2023-02-17 11:33:47 -03:00