Two changes worth mentioning:
`#instance` returns a fully configured embedding endpoint ready to use.
All endpoints respond to the same method and have the same signature - `perform!(text)`
This makes it easier to reuse them when generating embeddings in bulk.
* FIX/REFACTOR: FoldContent revamp
We hit a snag with our hot topic gist strategy: the regex we used to split the content didn't work, so we cannot send the original post separately. This was important for letting the model focus on what's new in the topic.
The algorithm doesn’t give us full control over how prompts are written, and figuring out how to format the content isn't straightforward. This means we're having to use more complicated workarounds, like regex.
To tackle this, I'm suggesting we simplify the approach a bit. Let's focus on summarizing as much as we can upfront, then gradually add new content until there's nothing left to summarize.
Also, the "extend" part is mostly for models with small context windows, which shouldn't pose a problem 99% of the time with the content volume we're dealing with.
* Fix fold docs
* Use #shift instead of #pop to get the first elem, not the last
* FEATURE: Set endpoint credentials directly from LlmModel.
Drop Llama2Tokenizer since we no longer use it.
* Allow http for custom LLMs
---------
Co-authored-by: Rafael Silva <xfalcox@gmail.com>
- Adds support for sd3 and sd3 turbo models - this requires new endpoints
- Adds a hack to normalize arrays in the tool calls
- Removes some leftover code
- Adds support for aspect ratio as well so you can generate wide or tall images
BAAI/bge-m3 is an interesting model, that is multilingual and with a
context size of 8192. Even with a 16x larger context, it's only 4x slower
to compute it's embeddings on the worst case scenario.
Also includes a minor refactor of the rake task, including setting model
and concurrency levels when running the backfill task.
* FIX: Handle unicode on tokenizer
Our fast track code broke when strings had characters who are longer in tokens than
in UTF-8.
Admins can set `DISCOURSE_AI_STRICT_TOKEN_COUNTING: true` in app.yml to ensure token counting is strict, even if slower.
Co-authored-by: wozulong <sidle.pax_0e@icloud.com>
* FEATURE: add support for new OpenAI embedding models
This adds support for just released text_embedding_3_small and large
Note, we have not yet implemented truncation support which is a
new API feature. (triggered using dimensions)
* Tiny side fix, recalc bots when ai is enabled or disabled
* FIX: downsample to 2000 items per vector which is a pgvector limitation
* 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
Previously endpoint/base would `+=` decoded_chunk to leftover
This could lead to cases where the leftover buffer had duplicate
previously processed data
Fix ensures we properly skip previously decoded data.
Keep in mind:
- GPT-4 is only going to be fully released next year - so this hardcodes preview model for now
- Fixes streaming bugs which became a big problem with GPT-4 turbo
- Adds Azure endpoing for turbo as well
Co-authored-by: Martin Brennan <martin@discourse.org>
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
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>
Per: https://platform.openai.com/docs/api-reference/authentication
There is an organization option which is useful for large orgs
> For users who belong to multiple organizations, you can pass a header to specify which organization is used for an API request. Usage from these API requests will count against the specified organization's subscription quota.
llm_triage supported claude 2 in triage, this implements it
OpenAI rate limits frequently, this introduces some exponential
backoff (3 attempts - 3 seconds, 9 and 27)
Also reduces temp of classifiers so they have consistent behavior
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
Open AI support function calling, this has a very specific shape
that other LLMs have not quite adopted.
This simulates a command framework using system prompts on LLMs
that are not open AI.
Features include:
- Smart system prompt to steer the LLM
- Parameter validation (we ensure all the params are specified correctly)
This is being tested on Anthropic at the moment and intial results
are promising.
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
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.
* DEV: Better strategies for summarization
The strategy responsibility needs to be "Given a collection of texts, I know how to summarize them most efficiently, using the minimum amount of requests and maximizing token usage".
There are different token limits for each model, so it all boils down to two different strategies:
Fold all these texts into a single one, doing the summarization in chunks, and then build a summary from those.
Build it by combining texts in a single prompt, and truncate it according to your token limits.
While the latter is less than ideal, we need it for "bart-large-cnn-samsum" and "flan-t5-base-samsum", both with low limits. The rest will rely on folding.
* Expose summarized chunks to users
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.
Given latest GPT 3.5 16k which is both better steered and supports functions
we can now support rich bot integration.
Clunky system message based steering is removed and instead we use the
function framework provided by Open AI
For the time being smart commands only work consistently on GPT 4.
Avoid using any smart commands on the earlier models.
Additionally adds better error handling to Claude which sometimes streams
partial json and slightly tunes the search command.
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>
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.
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.
Also adds some tests around completions and supports additional params
such as top_p, temperature and max_tokens
This also migrates off Faraday to using Net::HTTP directly
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
Rafael dos Santos Silva
Roman Rizzi
Sam
Loïc Guitaut
Jarek Radosz
Roman Rizzi