Commit Graph

181 Commits

Author SHA1 Message Date
Sam 2ad743d246
FEATURE: Add GitHub Helper AI Bot persona and tools (#513)
Introduces a new AI Bot persona called 'GitHub Helper' which is specialized in assisting with GitHub-related tasks and questions. It includes the following key changes:

- Implements the GitHub Helper persona class with its system prompt and available tools
   
- Adds three new AI Bot tools for GitHub interactions:
  - github_file_content: Retrieves content of files from a GitHub repository
  - github_pull_request_diff: Retrieves the diff for a GitHub pull request
  - github_search_code: Searches for code in a GitHub repository
    
- Updates the AI Bot dialects to support the new GitHub tools

- Implements multiple function calls for standard tool dialect
2024-03-08 06:37:23 +11:00
Loïc Guitaut 6ae4218a96 DEV: Fix new Rubocop offenses 2024-03-06 15:23:29 +01:00
Sam 8b382d6098
FEATURE: support for claude opus and sonnet (#508)
This provides new support for messages API from Claude.

It is required for latest model access.

Also corrects implementation of function calls.

* Fix message interleving

* fix broken spec

* add new models to automation
2024-03-06 06:04:37 +11:00
Sam b7a96e3bcb
FIX: avoid all bot feedback loops (#507)
We need to ensure that under no circumstances feedback loops between
bots will emerge cause this can eat up a lot of tokens
2024-03-05 10:02:49 +11:00
Sam 77cf9e2cff
FIX: system persona non English save, missing bot pms
- FIX: only update system attributes when updating system persona
- FIX: update participant count by hand so bot messages show in inbox
 

Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com>
2024-03-04 09:56:59 +11:00
Sam c02794cf2e
FIX: support multiple tool calls (#502)
* FIX: support multiple tool calls

Prior to this change we had a hard limit of 1 tool call per llm
round trip. This meant you could not google multiple things at
once or perform searches across two tools.

Also:

- Hint when Google stops working
- Log topic_id / post_id when performing completions

* Also track id for title
2024-03-02 07:53:21 +11:00
Sam 59bab2bba3
FIX: stream messages when directly PMing a persona (#500)
previous to this fix we did not consider personas a bot in the
front end
2024-03-01 07:53:42 +11:00
Sam 9fb1430e40
FIX: support spaces within arguments for Open AI (#499)
Previous to this fix if a tool call ever streamed a SPACE alone,
we would eat it and ignore it, breaking params

Also fixes some tests to ensure they are actually called :)
2024-02-29 12:47:34 +11:00
Rafael dos Santos Silva 1b72a00d2c
FEATURE: Option for AI triage to send a post to the review queue (#498)
Option for AI triage to send a post to the review queue
2024-02-29 12:33:28 +11:00
Sam 484fd1435b
DEV: improve internal design of ai persona and bug fix (#495)
* DEV: improve internal design of ai persona and bug fix

- Fixes bug where OpenAI could not describe images
- Fixes bug where mentionable personas could not be mentioned unless overarching bot was enabled
- Improves internal design of playground and bot to allow better for non "bot" users
- Allow PMs directly to persona users (previously bot user would also have to be in PM)
- Simplify internal code


Co-authored-by: Martin Brennan <martin@discourse.org>
2024-02-28 16:46:32 +11:00
Sam d036f3fb8e
FEATURE: AI helper support in non English languages (#489)
* FEATURE: AI helper support in non English languages

This attempts some prompt engineering to coerce AI helper to answer
in the appropriate language.

Note mileage will vary, in testing GPT-4 produces the best results
GPT-3.5 can return OKish results.

* Extend non english support for GPT-4V image caption

* Update db/fixtures/ai_helper/603_completion_prompts.rb

---------

Co-authored-by: Rafael Silva <xfalcox@gmail.com>
2024-02-27 16:31:51 -03:00
Sam aabff87501
FIX: image generation in gemini was broken (#490)
We need to inject blank model answers after tool calls if absent
otherwise model will reject it.
2024-02-27 18:24:30 +11:00
Roman Rizzi 94ba0dadc2
SECURITY: Place a SSRF protection when calling services from the plugin. (#485)
The Faraday adapter and `FinalDestionation::HTTP` will protect us from admin-initiated SSRF attacks when interacting with the external services powering this plugin features.:
2024-02-21 17:14:50 -03:00
Sam 1f74a77e17
DEV: correct flaky spec (#475)
We were not properly expiring prompt cache
2024-02-19 15:21:55 +11:00
Sam 0fb87b00e2
FEATURE: new Discourse Helper persona (#473)
This persona searches Discourse Meta for help with Discourse and
points users at relevant posts.

It is somewhat similar to using "Forum Helper" on meta, with the
notable difference that we can not lean on semantic search so using
some prompt engineering we try to keep it simple.
2024-02-19 14:52:12 +11:00
Keegan George d66915ecc1
DEV: Make prompts available on `CurrentUserSerializer` (#472) 2024-02-16 10:57:14 -08:00
Sam 3a8d95f6b2
FEATURE: mentionable personas and random picker tool, context limits (#466)
1. Personas are now optionally mentionable, meaning that you can mention them either from public topics or PMs
       - Mentioning from PMs helps "switch" persona mid conversation, meaning if you want to look up sites setting you can invoke the site setting bot, or if you want to generate an image you can invoke dall e
        - Mentioning outside of PMs allows you to inject a bot reply in a topic trivially
     - We also add the support for max_context_posts this allow you to limit the amount of context you feed in, which can help control costs

2. Add support for a "random picker" tool that can be used to pick random numbers 

3. Clean up routing ai_personas -> ai-personas

4. Add Max Context Posts so users can control how much history a persona can consume (this is important for mentionable personas) 

Co-authored-by: Martin Brennan <martin@discourse.org>
2024-02-15 16:37:59 +11:00
Rafael dos Santos Silva 0dba6623a0
FIX: Better AI chat thread titles (#467)
* FIX: Better AI chat thread titles

- Fix quote removal when multi-line

- Use XML tags for better LLM output parsing

- Use stop_sequences for faster and less wasteful LLM calls

- Adds truncation as the last line of defense
2024-02-09 14:49:28 -03:00
Rafael dos Santos Silva bccb7efdd6
FIX: Use a dedicated prompt for thread titles (#464) 2024-02-07 15:05:50 -03:00
Sam ba3c3951cf
FIX: typo causing text_embedding_3_large to fail (#460) 2024-02-05 11:16:36 +11:00
Sam a3c827efcc
FEATURE: allow personas to supply top_p and temperature params (#459)
* FEATURE: allow personas to supply top_p and temperature params

Code assistance generally are more focused at a lower temperature
This amends it so SQL Helper runs at 0.2 temperature vs the more
common default across LLMs of 1.0.

Reduced temperature leads to more focused, concise and predictable
answers for the SQL Helper

* fix tests

* This is not perfect, but far better than what we do today

Instead of fishing for

1. Draft sequence
2. Draft body

We skip (2), this means the composer "only" needs 1 http request to
open, we also want to eliminate (1) but it is a bit of a trickier
core change, may figure out how to pull it off (defer it to first draft save)

Value of bot drafts < value of opening bot conversations really fast
2024-02-03 07:09:34 +11:00
Roman Rizzi fba9c1bf2c
UX: Re-introduce embedding settings validations (#457)
* Revert "Revert "UX: Validate embeddings settings (#455)" (#456)"

This reverts commit 392e2e8aef.

* Resstore previous default
2024-02-01 16:54:09 -03:00
Roman Rizzi 392e2e8aef
Revert "UX: Validate embeddings settings (#455)" (#456)
This reverts commit 85fca89e01.
2024-02-01 14:06:51 -03:00
Roman Rizzi 85fca89e01
UX: Validate embeddings settings (#455) 2024-02-01 13:05:38 -03:00
Sam dcafc8032f
FIX: improve embedding generation (#452)
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
2024-01-31 10:38:47 -03:00
Sam ab7e9e31aa
FEATURE: allow excluding tags and categories from LLM report (#447)
Also

- Better diagnostics, output model being used
- Prompt LLM that true content is being injected in <context> tag
2024-01-30 15:55:05 +11:00
Roman Rizzi bae71eb047
FIX: Include provider in automation models (#446) 2024-01-29 18:07:29 -03:00
Roman Rizzi 0634b85a81
UX: Validations to LLM-backed features (except AI Bot) (#436)
* UX: Validations to Llm-backed features (except AI Bot)

This change is part of an ongoing effort to prevent enabling a broken feature due to lack of configuration. We also want to explicit which provider we are going to use. For example, Claude models are available through AWS Bedrock and Anthropic, but the configuration differs.

Validations are:

* You must choose a model before enabling the feature.
* You must turn off the feature before setting the model to blank.
* You must configure each model settings before being able to select it.

* Add provider name to summarization options

* vLLM can technically support same models as HF

* Check we can talk to the selected model

* Check for Bedrock instead of anthropic as a site could have both creds setup
2024-01-29 16:04:25 -03:00
Rafael dos Santos Silva 04bc402aae
FEATURE: Setting to control per post embeddings (#439)
* FEATURE: Setting to control per post embeddings
2024-01-23 22:09:27 -03:00
Jarek Radosz 5802cd1a0c
DEV: Fix various typos (#434) 2024-01-19 12:51:26 +01:00
Roman Rizzi 5bdf3dc1f4
DEV: Stop using shared_examples for endpoint specs (#430) 2024-01-17 15:08:49 -03:00
Sam 05d8b021f1
FIX: scrub invalid prompts when truncating (#426)
When you trim a prompt we never want to have a state where there
is a "tool" reply without a corresponding tool call, it makes no
sense

Also

- GPT-4-Turbo is 128k, fix that
- Claude was not preserving username in prompt
- We were throwing away unicode usernames instead of adding to
message
2024-01-16 13:48:00 +11:00
Roman Rizzi ff4da6ace8
FIX: Clean unicode usernames when adding messages through prompt's contrstuctor (#425) 2024-01-15 12:01:40 -03:00
Sam 825f01cfb2
FEATURE: even smoother streaming (#420)
Account properly for function calls, don't stream through <details> blocks
- Rush cooked content back to client
- Wait longer (up to 60 seconds) before giving up on streaming
- Clean up message bus channels so we don't have leftover data
- Make ai streamer much more reusable and much easier to read
- If buffer grows quickly, rush update so you are not artificially waiting
- Refine prompt interface
- Fix lost system message when prompt gets long
2024-01-15 18:51:14 +11:00
Jarek Radosz 6b8a57d957
DEV: Update linting (#423)
Co-authored-by: Keegan George <kgeorge13@gmail.com>
2024-01-13 00:28:06 +01:00
Roman Rizzi 04eae76f68
REFACTOR: Represent generic prompts with an Object. (#416)
* 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>
2024-01-12 14:36:44 -03:00
Rafael dos Santos Silva 3be76ebd7a
FEATURE: Move the default embeddings model to bge-large-en (#417) 2024-01-11 14:16:25 -03:00
Sam 8df966e9c5
FEATURE: smooth streaming of AI responses on the client (#413)
This PR introduces 3 things:

1. Fake bot that can be used on local so you can test LLMs, to enable on dev use:

SiteSetting.ai_bot_enabled_chat_bots = "fake"

2. More elegant smooth streaming of progress on LLM completion

This leans on JavaScript to buffer and trickle llm results through. It also amends it so the progress dot is much 
more consistently rendered

3. It fixes the Claude dialect 

Claude needs newlines **exactly** at the right spot, amended so it is happy 

---------

Co-authored-by: Martin Brennan <martin@discourse.org>
2024-01-11 15:56:40 +11:00
Roman Rizzi abde82c1f3
FIX: Use claude-2.1 to enable system prompts (#411) 2024-01-09 14:10:20 -03:00
Sam 05f7808057
FEATURE: more elegant progress (#409)
Previous to this change it was very hard to tell if completion was
stuck or not.

This introduces a "dot" that follows the completion and starts
flashing after 5 seconds.
2024-01-09 09:20:28 -03:00
Sam b0a0cbe3ca
FIX: improve bot behavior (#408)
* FIX: improve bot behavior

- Provide more information to Gemini context post function execution
- Use system prompts for Claude (fixes Dall E)
- Ensure Assistant is properly separated
- Teach Claude to return arrays in JSON vs XML

Also refactors tests so we do not copy tool preamble everywhere

* System msg is claude-2 only. fix typo

---------

Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2024-01-08 10:28:03 -03:00
Roman Rizzi 6124f910c1
FIX: Bring back Azure support. (#407)
We thought Azure's latest API version didn't have tool support yet, but I didn't understand it was complaining about a required field in the tool call message.
2024-01-05 17:08:10 -03:00
Sam 17cc09ec9c
FIX: don't include <details> in context (#406)
* FIX: don't include <details> in context

We need to be careful adding <details> into context of conversations
it can cause LLMs to hallucinate results

* Fix Gemini multi-turn ctx flattening

---------

Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2024-01-05 15:21:14 -03:00
Keegan George 7201d482d5
FEATURE: Add DallE support to AI helper's illustrate post (#404) 2024-01-05 09:03:23 -08:00
Sam dd42a4e47b
FIX: array arguments not parsed correctly (#405)
DALL E command accepts an Array as a tool argument, this was not
parsed correctly by the invoker leading to errors generating
images with DALL E

Side quest ... don't use update! it calls validations and will now
fail due to email validation
2024-01-05 14:39:32 +11:00
Roman Rizzi 971e03bdf2
FEATURE: AI Bot Gemini support. (#402)
It also corrects the syntax around tool support, which was wrong.

Gemini doesn't want us to include messages about previous tool invocations, so I had to shuffle around some code to send the response it generated from those invocations instead. For this, I created the "multi_turn" context, which bundles all the context involved in the interaction.
2024-01-04 18:15:34 -03:00
Roman Rizzi f9d7d7f5f0
DEV: AI bot migration to the Llm pattern. (#343)
* DEV: AI bot migration to the Llm pattern.

We added tool and conversation context support to the Llm service in discourse-ai#366, meaning we met all the conditions to migrate this module.

This PR migrates to the new pattern, meaning adding a new bot now requires minimal effort as long as the service supports it. On top of this, we introduce the concept of a "Playground" to separate the PM-specific bits from the completion, allowing us to use the bot in other contexts like chat in the future. Commands are called tools, and we simplified all the placeholder logic to perform updates in a single place, making the flow more one-wayish.

* Followup fixes based on testing

* Cleanup unused inference code

* FIX: text-based tools could be in the middle of a sentence

* GPT-4-turbo support

* Use new LLM API
2024-01-04 10:44:07 -03:00
Sam 03fc94684b
FIX: AI helper not working correctly with mixtral (#399)
* 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
2024-01-04 09:53:47 -03:00
Keegan George 1a5985134a
FIX: Show illustrate post only if stability API key present (#395) 2024-01-02 11:24:16 -08:00
Roman Rizzi 4182af230a
FIX: Correctly translate and read tools for Claude and Chat GPT. (#393)
I tested against the live models for the AI bot migration. It ensures Open AI's tool syntax is correct and we can correctly read the replies.
:
2024-01-02 11:21:13 -03:00