Commit Graph

230 Commits

Author SHA1 Message Date
Sam 61890b667c
FEATURE: search command now support searching in context of user (#610)
This optional feature allows search to be performed in the context
of the user that executed it.

By default we do not allow this behavior cause it means llm gets
access to potentially secure data.
2024-05-10 11:32:34 +10:00
Sam cf34838a09
FIX: context repairs for @mentioned bot (#608)
When the bot is @mentioned, we need to be a lot more careful
about constructing context otherwise bot gets ultra confused.

This changes multiple things:

1. We were omitting all thread first messages (fixed)
2. Include thread title (if available) in context
3. Construct context in a clearer way separating user request from data
2024-05-08 18:44:04 +10:00
Joffrey JAFFEUX dacc1b9f28
DEV: updates spec following changes in chat (#604)
Also makes this spec to use the `update_message!` helper.
2024-05-07 15:01:06 +02:00
Sam ab78d9b597
REFACTOR: Simplify tool invocation by removing bot_user and llm parameters (#603)
* Well, it was quite a journey but now tools have "context" which
can be critical for the stuff they generate

This entire change was so Dall E and Artist generate images in the correct context

* FIX: improve error handling around image generation

- also corrects image markdown and clarifies code

* fix spec
2024-05-07 21:55:46 +10:00
Sam 88c7427fab
FEATURE: allow @mentioning an ai bot in a channel (#602)
if a persona is mentionable and allows chat allow it to be mentioned in a chat channel
2024-05-07 10:30:39 +10:00
Sam e4b326c711
FEATURE: support Chat with AI Persona via a DM (#488)
Add support for chat with AI personas

- Allow enabling chat for AI personas that have an associated user
- Add new setting `allow_chat` to AI persona to enable/disable chat
- When a message is created in a DM channel with an allowed AI persona user, schedule a reply job
- AI replies to chat messages using the persona's `max_context_posts` setting to determine context
- Store tool calls and custom prompts used to generate a chat reply on the `ChatMessageCustomPrompt` table
- Add tests for AI chat replies with tools and context

At the moment unlike posts we do not carry tool calls in the context.

No @mention support yet for ai personas in channels, this is future work
2024-05-06 09:49:02 +10:00
Sam 32b3004ce9
FEATURE: Add Question Consolidator for robust Upload support in Personas (#596)
This commit introduces a new feature for AI Personas called the "Question Consolidator LLM". The purpose of the Question Consolidator is to consolidate a user's latest question into a self-contained, context-rich question before querying the vector database for relevant fragments. This helps improve the quality and relevance of the retrieved fragments.

Previous to this change we used the last 10 interactions, this is not ideal cause the RAG would "lock on" to an answer. 

EG:

- User: how many cars are there in europe
- Model: detailed answer about cars in europe including the term car and vehicle many times
- User: Nice, what about trains are there in the US

In the above example "trains" and "US" becomes very low signal given there are pages and pages talking about cars and europe. This mean retrieval is sub optimal. 

Instead, we pass the history to the "question consolidator", it would simply consolidate the question to "How many trains are there in the United States", which would make it fare easier for the vector db to find relevant content. 

The llm used for question consolidator can often be less powerful than the model you are talking to, we recommend using lighter weight and fast models cause the task is very simple. This is configurable from the persona ui.

This PR also removes support for {uploads} placeholder, this is too complicated to get right and we want freedom to shift RAG implementation. 

Key changes:

1. Added a new `question_consolidator_llm` column to the `ai_personas` table to store the LLM model used for question consolidation.

2. Implemented the `QuestionConsolidator` module which handles the logic for consolidating the user's latest question. It extracts the relevant user and model messages from the conversation history, truncates them if needed to fit within the token limit, and generates a consolidated question prompt.

3. Updated the `Persona` class to use the Question Consolidator LLM (if configured) when crafting the RAG fragments prompt. It passes the conversation context to the consolidator to generate a self-contained question.

4. Added UI elements in the AI Persona editor to allow selecting the Question Consolidator LLM. Also made some UI tweaks to conditionally show/hide certain options based on persona configuration.

5. Wrote unit tests for the QuestionConsolidator module and updated existing persona tests to cover the new functionality.

This feature enables AI Personas to better understand the context and intent behind a user's question by consolidating the conversation history into a single, focused question. This can lead to more relevant and accurate responses from the AI assistant.
2024-04-30 13:49:21 +10:00
Sam 85734fef52
FIX: properly cache user locale (#593)
This blob is localized according to user locale, so we can end up
bleeding incorrect data in the cache
2024-04-26 09:28:35 -03:00
Roman Rizzi 0c4069ab3f
DEV: Remove non-LLM-based summarization strategies. (#589)
We removed these services from our hosting two weeks ago. It's safe to assume everyone has moved to other LLM-based options.
2024-04-23 12:11:04 -03:00
Sam 4d8b7742da
FIX: many missing topics when categories excluded (#585)
We were forgetting about the NULL parent_category_id handling in
our check for sub categories
2024-04-23 08:53:51 +10:00
Rafael dos Santos Silva 595cde0fd6
FIX: Users with empty locales would error out during prompt localization (#584) 2024-04-22 13:55:10 -03:00
Sam 5ab86923ff
FIX: when excluding categories also exclude children (#583)
This allows you to exclude trees of categories in a simple way

It also means you can no longer exclude "just the parent" but
this is a fair compromise.
2024-04-22 16:05:24 +10:00
Sam 4a29f8ed1c
FEATURE: Enhance AI debugging capabilities and improve interface adjustments (#577)
* FIX: various RAG edge cases

- Nicer text to describe RAG, avoids the word RAG
- Do not attempt to save persona when removing uploads and it is not created
- Remove old code that avoided touching rag params on create

* FIX: Missing pause button for persona users

* Feature: allow specific users to debug ai request / response chains

This can help users easily tune RAG and figure out what is going
on with requests.

* discourse helper so it does not explode

* fix test

* simplify implementation
2024-04-15 23:22:06 +10:00
Sam f6ac5cd0a8
FEATURE: allow tuning of RAG generation (#565)
* FEATURE: allow tuning of RAG generation

- change chunking to be token based vs char based (which is more accurate)
- allow control over overlap / tokens per chunk and conversation snippets inserted
- UI to control new settings

* improve ui a bit

* fix various reindex issues

* reduce concurrency

* try ultra low queue ... concurrency 1 is too slow.
2024-04-12 10:32:46 -03:00
Rafael dos Santos Silva 253e0b7b39
FEATURE: Mixtral/Mistral/Haiku Automation Support (#571)
Adds new models to automation, and makes LLM output parsing more robust.
2024-04-11 09:50:46 -03:00
Sam 3b0cfdbe5c
FIX: throwing away first file in diff (#573)
We were chucking out the first file in a PR diff due to a
logic bug
2024-04-11 13:26:58 +10:00
Bianca Nenciu 505650205d
FIX: Fetch categories data using specific endpoint (#543)
It used to fetch it from /site.json, but /categories.json is the more
appropriate one. This one also implements pagination, so we have to do
one request per page.
2024-04-08 11:33:20 +03:00
Roman Rizzi 1f1c94e5c6
FEATURE: AI Bot RAG support. (#537)
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
2024-04-01 13:43:34 -03:00
Sam fb81307c59
FEATURE: web browsing tool (#548)
This pull request makes several improvements and additions to the GitHub-related tools and personas in the `discourse-ai` repository:

1. It adds the `WebBrowser` tool to the  `Researcher` persona, allowing the AI to visit web pages, retrieve HTML content, extract the main content, and convert it to plain text.

2. It updates the `GithubFileContent`, `GithubPullRequestDiff`, and `GithubSearchCode` tools to handle HTTP responses more robustly (introducing size limits). 

3. It refactors the `send_http_request` method in the `Tool` class to follow redirects when specified, and to read the response body in chunks to avoid memory issues with large responses. (only for WebBrowser)

4. It updates the system prompt for the `Researcher` persona to provide more detailed guidance on when to use Google search vs web browsing, and how to optimize tool usage and reduce redundant requests.

5. It adds a new `web_browser_spec.rb` file with tests for the `WebBrowser` tool, covering various scenarios like handling different HTML structures and following redirects.
2024-03-28 16:01:58 +11:00
Sam 61e4c56e1a
FEATURE: Add vision support to AI personas (Claude 3) (#546)
This commit adds the ability to enable vision for AI personas, allowing them to understand images that are posted in the conversation.

For personas with vision enabled, any images the user has posted will be resized to be within the configured max_pixels limit, base64 encoded and included in the prompt sent to the AI provider.

The persona editor allows enabling/disabling vision and has a dropdown to select the max supported image size (low, medium, high). Vision is disabled by default.

This initial vision support has been tested and implemented with Anthropic's claude-3 models which accept images in a special format as part of the prompt.

Other integrations will need to be updated to support images.

Several specs were added to test the new functionality at the persona, prompt building and API layers.

 - Gemini is omitted, pending API support for Gemini 1.5. Current Gemini bot is not performing well, adding images is unlikely to make it perform any better.

 - Open AI is omitted, vision support on GPT-4 it limited in that the API has no tool support when images are enabled so we would need to full back to a different prompting technique, something that would add lots of complexity


---------

Co-authored-by: Martin Brennan <martin@discourse.org>
2024-03-27 14:30:11 +11:00
Sam 41f1530078
FIX: mention suppression was not working right (#538)
We were only suppressing non mentions, ones that become spans.

@sam in the test was not resolving to a mention cause the user
did not exist.

depends on: https://github.com/discourse/discourse/pull/26253 for tests to pass.
2024-03-20 13:00:39 +11:00
Sam cc0369dd39
FEATURE: friendlier reply behavior in bot PMs (#535)
- Stop replying as bot, when human replies to another human
- Reply as correct persona when replying directly to a persona
- Fix paper cut where suppressing notifications was not doing so
2024-03-19 20:15:12 +11:00
Sam d7ed8180af
FEATURE: allow suppression of notifications from report generation (#533)
* FEATURE: allow suppression of notifications from report generation

Previously we needed to do this by hand, unfortunately this uses up
too many tokens and is very hard to discover.

New option means that we can trivially disable notifications without
needing any prompt engineering.

* URI.parse is safer, use it
2024-03-16 08:05:03 +11:00
Sam a03bc6ddec
FEATURE: Share conversations with AI via a URL (#521)
This allows users to share a static page of an AI conversation with
the rest of the world.

By default this feature is disabled, it is enabled by turning on
ai_bot_allow_public_sharing via site settings

Precautions are taken when sharing

1. We make a carbonite copy
2. We minimize work generating page
3. We limit to 100 interactions
4. Many security checks - including disallowing if there is a mix
of users in the PM.

* Bonus commit, large PRs like this PR did not work with github tool
large objects would destroy context


Co-authored-by: Martin Brennan <martin@discourse.org>
2024-03-12 16:51:41 +11:00
Sam 79638c2f50
FIX: Tune function calling (#519)
Adds support for "name" on functions which can be used for tool calls

For function calls we need to keep track of id/name and previously
we only supported either

Also attempts to improve sql helper
2024-03-09 08:46:40 +11:00
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
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 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
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 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 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
Keegan George 1a5985134a
FIX: Show illustrate post only if stability API key present (#395) 2024-01-02 11:24:16 -08:00
Rafael dos Santos Silva 140359c2ef
FEATURE: Per post embeddings (#387) 2023-12-29 12:28:45 -03:00
Sam 37dd98c937
FIX: exclude non visible topics from report context (#375)
Generally non visible topics are not that interesting, do not add
this noise to the report context
2023-12-21 19:08:36 +11:00
Keegan George 7b4710d5c9
FEATURE: Generate post illustrations (#367) 2023-12-19 11:17:34 -08:00
Sam 529703b5ec
FEATURE: support sending AI report to an email address (#368)
Support emailing the AI report to any arbitrary email
2023-12-19 17:51:49 +11:00
Sam d0f54443ae
FEATURE: LLM based peroidical summary report (#357)
Introduce a Discourse Automation based periodical report. Depends on Discourse Automation.

Report works best with very large context language models such as GPT-4-Turbo and Claude 2.

- Introduces final_insts to generic llm format, for claude to work best it is better to guide the last assistant message (we should add this to other spots as well)
- Adds GPT-4 turbo support to generic llm interface
2023-12-19 12:04:15 +11:00
Krzysztof Kotlarek 6de9b9c274
DEV: Replace deprecated min_trust_to_create_post (#356)
In https://github.com/discourse/discourse/pull/24740, `min_trust_to_create_topic` site setting was replaced by `create_topic_allowed_groups`. This PR replaces the former, deprecated one, with the latter.
2023-12-14 14:07:28 +11:00
Sam 605445831f
FEATURE: try including views/username/likes in search results (#349)
This is somewhat experimental, but the context of likes/view/username
can help the llm find out what content is more important or even
common users that produce great content

This inflates the amount of tokens somewhat, but given it is all numbers
and search columns titles are only included once this is not severe
2023-12-12 12:22:28 +11:00
Sam a66b1042cc
FEATURE: scale up result count for search depending on model (#346)
We were limiting to 20 results unconditionally cause we had to make
sure search always fit in an 8k context window.

Models such as GPT 3.5 Turbo (16k) and GPT 4 Turbo / Claude 2.1 (over 150k)
allow us to return a lot more results.

This means we have a much richer understanding cause context is far
larger.

This also allows a persona to tweak this number, in some cases admin
may want to be conservative and save on tokens by limiting results

This also tweaks the `limit` param which GPT-4 liked to set to tell
model only to use it when it needs to (and describes default behavior)
2023-12-11 16:54:16 +11:00
Sam 6380ebd829
FEATURE: allow personas to provide command options (#331)
Personas now support providing options for commands.

This PR introduces a single option "base_query" for the SearchCommand. When supplied all searches the persona will perform will also include the pre-supplied filter.

This can allow personas to search a subset of the forum (such as documentation)

This system is extensible we can add options to any command trivially.
2023-12-08 08:42:56 +11:00
Roman Rizzi 450ec915d8
FIX: Make FoldContent strategy more resilient when using models with low token count. (#341)
We'll recursively summarize  the content into smaller chunks until we are sure we can concatenate
them without going over the token limit.
2023-12-06 19:00:24 -03:00
Martin Brennan 24370a9ca6
Revert "FIX: Use Guardian.basic_user instead of new (anon) (#332)" (#337)
This reverts commit a3a1285dc5.

c.f. https://github.com/discourse/discourse/pull/24742
2023-12-06 16:26:43 +10:00
Martin Brennan a3a1285dc5
FIX: Use Guardian.basic_user instead of new (anon) (#332)
c.f. de983796e1b66aa2ab039a4fb6e32cec8a65a098

There will soon be additional login_required checks
for Guardian, and the intent of many checks by automated
systems is better fulfilled by using BasicUser, which
simulates a logged in TL0 forum user, rather than an
anon user.
2023-12-06 12:01:41 +10:00
Roman Rizzi 3bc010b686
FIX: call the right method to summarize with truncation (#328) 2023-12-01 10:17:24 -03:00
Sam 6ddc17fd61
DEV: port directory structure to Zeitwerk (#319)
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.
2023-11-29 15:17:46 +11:00
Roman Rizzi f26adf2cf6
FIX: Use XML tags in generate_titles prompt. (#322)
We must ensure we can isolate titles, and the models sometimes ignore the example we give them.

Additionally, anons can generate HyDE posts, so we need to check if user is nil when attempting to log requests.
2023-11-28 12:52:22 -03:00
Roman Rizzi 775610b1c2
FIX: Chat titler was still using the old code after LLM migration (#314) 2023-11-27 13:03:24 -03:00
Roman Rizzi 54a8dd9556
REFACTOR: Use LLM abstraction in the AI Helper. (#312)
It also removes the need for multiple versions of our seeded prompts per model, further simplifying the code.
2023-11-27 09:33:31 -03:00
Sam 5a4598a7b4
FEATURE: Azure OpenAI support for DALL*E 3 (#313)
* FEATURE: Azure OpenAI support for DALL*E 3

Previous to this there was no way to add an inference endpoint for
DALL*E on Azure cause it requires custom URLs

Also:

- On save, when editing a persona it would revert priority and enabled
- More forgiving parsing in command framework for array function calls
- By default generate HD images - they tend to be a bit better
- Improve DALL*E prompt which was getting very annoying and always echoing what it is about to do
- Add a bit of a sleep between retries on image generation
- Fix error handling in image_command
2023-11-27 13:01:05 +11:00
Sam dff9f33a97
FEATURE: DALL-E-3 persona for image generation (#311)
* FIX: no selected persona should pick first prioritized one

Previously we were looking at `.personaId` but there is only an
id attribute so it failed

* FEATURE: new DALL-E-3 persona

This persona generates images using DALL-E-3 API and is enabled
by default

Keep in mind that we are still waiting on seeds/gen_id so we can
not retain style consistently between turns.

This will change as soon as a new Open AI API provides the missing
parameters

Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-24 18:08:08 +11:00
Sam 6282b6d21f
FIX: implement tools framework for Anthropic (#307)
Previous to this changeset we used a custom system for tools/command
support for Anthropic.

We defined commands by using !command as a signal to execute it

Following Anthropic Claude 2.1, there is an official supported syntax (beta)
for tools execution.

eg:

```
+      <function_calls>
+      <invoke>
+      <tool_name>image</tool_name>
+      <parameters>
+      <prompts>
+      [
+      "an oil painting",
+      "a cute fluffy orange",
+      "3 apple's",
+      "a cat"
+      ]
+      </prompts>
+      </parameters>
+      </invoke>
+      </function_calls>
```

This implements the spec per Anthropic, it should be stable enough
to also work on other LLMs.

Keep in mind that OpenAI is not impacted here at all, as it has its
own custom system for function calls.

Additionally:

- Fixes the title system prompt so it works with latest Anthropic
- Uses new spec for "system" messages by Anthropic
- Tweak forum helper persona to guide Anthropic a tiny be better

Overall results are pretty awesome and Anthropic Claude performs
really well now on Discourse
2023-11-24 06:39:56 +11:00
Roman Rizzi 3064d4c288
REFACTOR: Summarization and HyDE now use an LLM abstraction. (#297)
* DEV: One LLM abstraction to rule them all

* REFACTOR: HyDE search uses new LLM abstraction

* REFACTOR: Summarization uses the LLM abstraction

* Updated documentation and made small fixes. Remove Bedrock claude-2 restriction
2023-11-23 12:58:54 -03:00
Roman Rizzi e0691e70e8
DEV: Updates to the summarization strategy API (#301)
Introduced by discourse/discourse#24489

In the future, this change will let us log who requested the summary in the `AiApiAuditLog`.:
2023-11-21 13:27:35 -03:00
Sam 98c89953d3
FEATURE: remember previously selected persona (#299)
People tend to keep to 1 persona when working with the bot,
this adds local browser memory for the last persona you interacted
with so you do not need to select it over and over again.

This is per browser, not per user memory.

Also... clean up tests so they do not need to require stubs which
were breaking the build

---------

Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 17:02:27 +10:00
Sam 5b5edb22c6
FEATURE: UI to update ai personas on admin page (#290)
Introduces a UI to manage customizable personas (admin only feature)

Part of the change was some extensive internal refactoring:

- AIBot now has a persona set in the constructor, once set it never changes
- Command now takes in bot as a constructor param, so it has the correct persona and is not generating AIBot objects on the fly
- Added a .prettierignore file, due to the way ALE is configured in nvim it is a pre-req for prettier to work
- Adds a bunch of validations on the AIPersona model, system personas (artist/creative etc...) are all seeded. We now ensure
- name uniqueness, and only allow certain properties to be touched for system personas.
- (JS note) the client side design takes advantage of nested routes, the parent route for personas gets all the personas via this.store.findAll("ai-persona") then child routes simply reach into this model to find a particular persona.
- (JS note) data is sideloaded into the ai-persona model the meta property supplied from the controller, resultSetMeta
- This removes ai_bot_enabled_personas and ai_bot_enabled_chat_commands, both should be controlled from the UI on a per persona basis
- Fixes a long standing bug in token accounting ... we were doing to_json.length instead of to_json.to_s.length
- Amended it so {commands} are always inserted at the end unconditionally, no need to add it to the template of the system message as it just confuses things
- Adds a concept of required_commands to stock personas, these are commands that must be configured for this stock persona to show up.
- Refactored tests so we stop requiring inference_stubs, it was very confusing to need it, added to plugin.rb for now which at least is clearer
- Migrates the persona selector to gjs

---------

Co-authored-by: Joffrey JAFFEUX <j.jaffeux@gmail.com>
Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-21 16:56:43 +11:00
Sam a4f419f54f
FEATURE: basic infrastructure for custom personas (#288)
- New AiPersona model which can store custom personas
- Persona are restricted via group security
- They can contain custom system messages
- They can support a list of commands optionally

To avoid expensive DB calls in the serializer a Multisite friendly Hash was introduced (which can be expired on transaction commit)
2023-11-10 11:39:49 +11:00
Roman Rizzi d0198c5c5b
FIX: Changes to the sentiment reports. (#289)
This PR aims to clarify sentiment reports by replacing averages with a count of posts that have one of their values above a threshold (60), meaning we have some level of confidence they are, in fact, positive or negative.

Same thing happen with post emotions, with the difference that a post can have multiple values above it (30). Additionally, we dropped the "Neutral" axis.

We also reworded the tooltip next to each report title, and added an early return to signal we have no data available instead of displaying an empty chart.
2023-11-09 17:23:25 -03:00
Roman Rizzi 458e66aef9
FIX: Filter classification type using the correct column (#286) 2023-11-08 14:58:35 -03:00
Roman Rizzi 231cf91cc2
FIX: Don't divide by zero if there is no emotion data for TL group (#285) 2023-11-08 13:05:36 -03:00
Roman Rizzi b172ef11c4
FEATURE: Expose sentiment classifications via the admin dashboard. (#284)
This PR adds new reports for displaying information about post sentiments grouped by date and emotions group by TL.

Depends on discourse/discourse#24274
2023-11-08 10:50:37 -03:00
Sam fc65404896
FEATURE: support topic_id and post_id logging in ai audit log (#274)
This makes it easier to track who is responsible for a completion
in logs

Note: ai helper and summarization are not yet implemented
2023-11-01 08:41:31 +11:00
Sam 0b62c0fa02
FIX: keep parity of shape for image command (#275)
Function calling will start hallucinating if you reshape results.

Previously we were morphing from:

`{ prompts: ["prompt 1", "prompt 2"] }`

to

`{ prompts: { prompt: "prompt 1", seed: 222}, { ... `

This meant that over a few call sequences function_call starts hallucinating an incorrect shape.

This change grounds us even on GPT-3.5
2023-10-31 19:12:25 +11:00
Sam b06380d9fa
FIX: avoid semicolons at the end of queries for SQL Helper (#268)
This makes it easier to cut and paste snippets it is producing

Also fine tune the prompt in an attempt to hone gpt 3.5 which is very finicky
2023-10-27 16:21:09 +11:00
Sam 6add06af8f
FEATURE: Make artist more creative (#266)
This allows for 2 big features:

1. Artist can ship up to 4 prompts for image generation
2. Artist can regenerate images cause it is aware of seed

This allows for iteration on images maintaining visual style
2023-10-27 14:48:12 +11:00
David Battersby cda5cb6e9c
DEV: update test to use new chat message service (#254)
Update test to use the new chat update message service when editing chat messages.
2023-10-23 17:50:25 +08:00
David Battersby abd3da3383
DEV: skip edit message test until new service added to chat (#259)
Temporarily skip the edit chat message test as we are moving MessageUpdate to a new service in Chat.
2023-10-23 15:30:12 +08:00
Sam 1500308437
FEATURE: defer creation of bot users (#258)
Also fixes it so users without bot in header can send it messages.

Previous to this change we would seed all bots with database seeds.

This lead to lots of confusion for people who do not enable ai bot.

Instead:

1. We do not seed any bots **until** user enables the ai_bot_enabled setting
2. If it is disabled we will
  a. If no messages were created by bot - delete it
  b. Otherwise we will deactivate account
2023-10-23 17:00:58 +11:00
Sam f65e50bd9e
FIX: allow for blank fields in Google results (#255)
Under certain cases, for example:

```
there is this japanese band called kirimi, tell me more about them, try searching 3 times and at least 2 times in japanese before answering.
```

Results come back with blank snippets. This adds protection so this
is allowed and code does not simply blow up.
2023-10-19 14:44:59 +11:00