Commit Graph

524 Commits

Author SHA1 Message Date
Rafael dos Santos Silva aef9a03d4c
FEATURE: Truncate AI Captions to a reasonable max size (#907) 2024-11-12 15:52:46 -03:00
Sam e817b7dc11
FEATURE: improve tool support (#904)
This re-implements tool support in DiscourseAi::Completions::Llm #generate

Previously tool support was always returned via XML and it would be the responsibility of the caller to parse XML

New implementation has the endpoints return ToolCall objects.

Additionally this simplifies the Llm endpoint interface and gives it more clarity. Llms must implement

decode, decode_chunk (for streaming)

It is the implementers responsibility to figure out how to decode chunks, base no longer implements. To make this easy we ship a flexible json decoder which is easy to wire up.

Also (new)

    Better debugging for PMs, we now have a next / previous button to see all the Llm messages associated with a PM
    Token accounting is fixed for vllm (we were not correctly counting tokens)
2024-11-12 08:14:30 +11:00
Keegan George 644141ff08
FIX: Regenerate summary button still shows cached summary (#903)
This PR fixes an issue where clicking to regenerate a summary was still showing the cached summary. To resolve this we call resetSummary() to reset all the summarization related properties before creating a new request.
2024-11-07 16:01:18 -08:00
Roman Rizzi 9505a8976c
FEATURE: Automatically backfill regular summaries. (#892)
This change introduces a job to summarize topics and cache the results automatically. We provide a setting to control how many topics we'll backfill per hour and what the topic's minimum word count is to qualify.

We'll prioritize topics without summary over outdated ones.
2024-11-04 17:48:11 -03:00
Sam 98022d7d96
FEATURE: support custom instructions for persona streaming (#890)
This allows us to inject information into the system prompt
which can help shape replies without repeating over and over
in messages.
2024-11-05 07:43:26 +11:00
Rafael dos Santos Silva 772ee934ab
Migrate sentiment to a TEI backend (#886) 2024-11-04 09:14:34 -03:00
Sam bffe9dfa07
FIX: we must properly encode objects prior to escaping (#891)
in cases of arrays escapeHTML will not work)

*
2024-11-04 16:16:25 +11:00
Sam c352054d4e
FIX: encode parameters returned from LLMs correctly (#889)
Fixes encoding of params on LLM function calls.

Previously we would improperly return results if a function parameter returned an HTML tag.

Additionally adds some missing HTTP verbs to tool calls.
2024-11-04 10:07:17 +11:00
Roman Rizzi 7e3a543f6f
FEATURE: Double gist length to 40 words (#888) 2024-11-01 13:09:03 -03:00
Roman Rizzi e8f0633141
DEV: Extend truncation to all summarizable content (#884) 2024-10-31 12:17:42 -03:00
Roman Rizzi e8eed710e0
FIX: Truncate OP for gists to help the model focus on the latest posts (#883) 2024-10-31 10:54:56 -03:00
Sam 34a59b623e
FIX: ensure replies are never double streamed (#879)
The custom field "discourse_ai_bypass_ai_reply" was added so
we can signal the post created hook to bypass replying even
if it thinks it should.

Otherwise there are cases where we double answer user questions
leading to much confusion.

This also slightly refactors code making the controller smaller
2024-10-30 20:24:39 +11:00
Sam be0b78cacd
FEATURE: new endpoint for directly accessing a persona (#876)
The new `/admin/plugins/discourse-ai/ai-personas/stream-reply.json` was added.

This endpoint streams data direct from a persona and can be used
to access a persona from remote systems leaving a paper trail in
PMs about the conversation that happened

This endpoint is only accessible to admins.

---------

Co-authored-by: Gabriel Grubba <70247653+Grubba27@users.noreply.github.com>
Co-authored-by: Keegan George <kgeorge13@gmail.com>
2024-10-30 10:28:20 +11:00
Roman Rizzi dd404c924a
DEV: Use different feature_names for summarization strategies (#875) 2024-10-29 08:45:14 -03:00
Rafael dos Santos Silva 8ded4b2e58
FIX: Use present? instead of invalid exists? (#869) 2024-10-25 13:04:42 -03:00
Roman Rizzi a2b1ea3c63
FEATURE: Fast-track gist regeneration when a hot topic gets a new post (#860)
* FEATURE: Fast-track gist regeneration when a hot topic gets a new post

* DEV: Introduce an upsert-like summarize

* FIX: Only enqueue fast-track gist for hot hot hot topics

---------

Co-authored-by: Rafael Silva <xfalcox@gmail.com>
2024-10-25 12:38:49 -03:00
Rafael dos Santos Silva 33da27e231
FIX: Change hot gist prompt to avoid title repeating #859 (#859)
Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2024-10-25 12:12:33 -03:00
Roman Rizzi ec97996905
FIX/REFACTOR: FoldContent revamp (#866)
* 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
2024-10-25 11:51:17 -03:00
Sam 12869f2146
FIX: testing tool was not showing rag results (#867)
This changeset contains 4 fixes:

1. We were allowing running tests on unsaved tools,
this is problematic cause uploads are not yet associated or indexed
leading to confusing results. We now only show the test button when
tool is saved.


2. We were not properly scoping rag document fragements, this
meant that personas and ai tools could get results from other
unrelated tools, just to be filtered out later


3. index.search showed options as "optional" but implementation
required the second option

4. When testing tools searching through document fragments was
not working at all cause we did not properly load the tool
2024-10-25 16:01:25 +11:00
Sam 4923837165
FIX: Llm selector / forced tools / search tool (#862)
* FIX: Llm selector / forced tools / search tool


This fixes a few issues:

1. When search was not finding any semantic results we would break the tool
2. Gemin / Anthropic models did not implement forced tools previously despite it being an API option
3. Mechanics around displaying llm selector were not right. If you disabled LLM selector server side persona PM did not work correctly.
4. Disabling native tools for anthropic model moved out of a site setting. This deliberately does not migrate cause this feature is really rare to need now, people who had it set probably did not need it.
5. Updates anthropic model names to latest release

* linting

* fix a couple of tests I missed

* clean up conditional
2024-10-25 06:24:53 +11:00
Rafael dos Santos Silva 3022d34613
FEATURE: Support srv records for OpenAI compatible LLMs (#865) 2024-10-24 15:47:12 -03:00
Rafael dos Santos Silva 96f5f8cbd0
FIX: Basic cleanup of AI Caption to remove line breaks and pipes (#857) 2024-10-23 18:38:29 -03:00
Sam f1283e156d
FEATURE: allow scoping of google tool queries (#852)
This allows to simply scope search results to specific domains and prepend arbitrary snippets to searches made
2024-10-23 16:55:10 +11:00
Sam 059d3b6fd2
FEATURE: better logging for automation reports (#853)
A new feature_context json column was added to ai_api_audit_logs

This allows us to store rich json like context on any LLM request
made.

This new field now stores automation id and name.

Additionally allows llm_triage to specify maximum number of tokens

This means that you can limit the cost of llm triage by scanning only
first N tokens of a post.
2024-10-23 16:49:56 +11:00
Sam a1f859a415
FEATURE: improve visibility of AI usage in LLM page (#845)
This changeset: 

1. Corrects some issues with "force_default_llm" not applying
2. Expands the LLM list page to show LLM usage
3. Clarifies better what "enabling a bot" on an llm means (you get it in the selector)
2024-10-22 11:16:02 +11:00
Roman Rizzi 3533814870
UX: Avoid introductory phrases and summarize topics without replies (#848) 2024-10-21 17:53:48 -03:00
Roman Rizzi 6d504ab80d
FEATURE: Make hot topic gists opt-in. (#846)
This change restricts gists to members of specific groups. It also fixes a bug where other lists could display the gist if available.
2024-10-21 15:15:25 -03:00
Roman Rizzi 27b5542357
FEATURE: Generate topic gists for the hot topics list. (#837)
* Display gists in the hot topics list

* Adjust hot topics gist strategy and add a job to generate gists

* Replace setting with a configurable batch size

* Avoid loading summaries for other topic lists

* Tweak gist prompt to focus on latest posts in the context of the OP

* Remove serializer hack and rely on core change from discourse/discourse#29291

* Update lib/summarization/strategies/hot_topic_gists.rb

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

---------

Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
2024-10-18 18:01:39 -03:00
Rafael dos Santos Silva decf1bb49d
FIX: api key header error (#839)
* FIX: api key header error

* FIX: remove unnecessary headers

* FIX: a error

* FEATURE: Add both headers

---------

Co-authored-by: 耗子 <i@haozi.net>
2024-10-16 15:57:36 -03:00
Kris 25cc03809a
DEV: ensure far-copy icon is included in subset (#841) 2024-10-16 12:32:13 -04:00
Rafael dos Santos Silva 792703c942
FEATURE: Discord Bot integration (#831)
This adds support for the a Discord bot that can search in a Discourse instance when invoked via slash commands in Discord Guild channel.
2024-10-16 12:41:18 -03:00
Martin Brennan d7745d1ac3
FIX: Remove missed AiPersona.allowed_chat (#838)
Followup bdf3b6268b

I think this is the fix but not sure how to test it,
this is breaking the build
2024-10-16 10:33:24 +11:00
Sam bdf3b6268b
FEATURE: smarter persona tethering (#832)
Splits persona permissions so you can allow a persona on:

- chat dms
- personal messages
- topic mentions
- chat channels

(any combination is allowed)

Previously we did not have this flexibility.

Additionally, adds the ability to "tether" a language model to a persona so it will always be used by the persona. This allows people to use a cheaper language model for one group of people and more expensive one for other people
2024-10-16 07:20:31 +11:00
Roman Rizzi c7acb4a6a0
REFACTOR: Support of different summarization targets/prompts. (#835)
* DEV: Add summary types

* Refactor for different summary types

* Use enum for summary types

* Update lib/summarization/strategies/topic_summary.rb

Co-authored-by: Penar Musaraj <pmusaraj@gmail.com>

* Update lib/summarization/strategies/topic_gist.rb

Co-authored-by: Penar Musaraj <pmusaraj@gmail.com>

* Update lib/summarization/strategies/chat_messages.rb

Co-authored-by: Penar Musaraj <pmusaraj@gmail.com>

* Fix chat_messages single prompt

* Small tweak to the chat summarization prompt

---------

Co-authored-by: Penar Musaraj <pmusaraj@gmail.com>
2024-10-15 13:53:26 -03:00
Rafael dos Santos Silva 791fad1e6a
FEATURE: Index embeddings using bit vectors (#824)
On very large sites, the rare cache misses for Related Topics can take around 200ms, which affects our p99 metric on the topic page. In order to mitigate this impact, we now have several tools at our disposal.

First, one is to migrate the index embedding type from halfvec to bit and change the related topic query to leverage the new bit index by changing the search algorithm from inner product to Hamming distance. This will reduce our index sizes by 90%, severely reducing the impact of embeddings on our storage. By making the related query a bit smarter, we can have zero impact on recall by using the index to over-capture N*2 results, then re-ordering those N*2 using the full halfvec vectors and taking the top N. The expected impact is to go from 200ms to <20ms for cache misses and from a 2.5GB index to a 250MB index on a large site.

Another tool is migrating our index type from IVFFLAT to HNSW, which can increase the cache misses performance even further, eventually putting us in the under 5ms territory. 

Co-authored-by: Roman Rizzi <roman@discourse.org>
2024-10-14 13:26:03 -03:00
Hoa Nguyen 94010a5f78
FEATURE: Tools for models from Ollama provider (#819)
Adds support for Ollama function calling
2024-10-11 07:25:53 +11:00
Sam 6c4c96e83c
FEATURE: allow persona to only force tool calls on limited replies (#827)
This introduces another configuration that allows operators to
limit the amount of interactions with forced tool usage.

Forced tools are very handy in initial llm interactions, but as
conversation progresses they can hinder by slowing down stuff
and adding confusion.
2024-10-11 07:23:42 +11:00
Mark VanLandingham 52d90cf1bc
DEV: Add apply_modifier for SemanticTopicQuery topics list (#830) 2024-10-10 12:13:16 -05:00
Sam e1a0eb6131
FEATURE: support chain halting and upload creation support (#821)
This adds chain halting (ability to terminate llm chain in a tool)
and the ability to create uploads in a tool

Together this lets us integrate custom image generators into a
custom tool.
2024-10-09 08:17:45 +11:00
Sam 545500b329
FEATURE: allows forced LLM tool use (#818)
* FEATURE: allows forced LLM tool use

Sometimes we need to force LLMs to use tools, for example in RAG
like use cases we may want to force an unconditional search.

The new framework allows you backend to force tool usage.

Front end commit to follow

* UI for forcing tools now works, but it does not react right

* fix bugs

* fix tests, this is now ready for review
2024-10-05 09:46:57 +10:00
Sam c294b6d394
FEATURE: allow llm triage to automatically hide posts (#820)
Previous to this change we could flag, but there was no way
to hide content and treat the flag as spam.

We had the option to hide topics, but this is not desirable for
a spam reply.

New option allows triage to hide a post if it is a reply, if the
post happens to be the first post on the topic, the topic will
be hidden.
2024-10-04 16:11:30 +10:00
Hoa Nguyen 2063b3854f
FEATURE: Add Ollama provider (#812)
This allows our users to add the Ollama provider and use it to serve our AI bot (completion/dialect).

In this PR, we introduce:

    DiscourseAi::Completions::Dialects::Ollama which would help us translate by utilizing Completions::Endpoint::Ollama
    Correct extract_completion_from and partials_from in Endpoints::Ollama

Also

    Add tests for Endpoints::Ollama
    Introduce ollama_model fabricator
2024-10-01 10:45:03 +10:00
Sam 5cbc9190eb
FEATURE: RAG search within tools (#802)
This allows custom tools access to uploads and sophisticated searches using embedding.

It introduces:

 - A shared front end for listing and uploading files (shared with personas)
 -  Backend implementation of index.search function within a custom tool.

Custom tools now may search through uploaded files

function invoke(params) {
   return index.search(params.query)
}

This means that RAG implementers now may preload tools with knowledge and have high fidelity over
the search.

The search function support

    specifying max results
    specifying a subset of files to search (from uploads)

Also

 - Improved documentation for tools (when creating a tool a preamble explains all the functionality)
  - uploads were a bit finicky, fixed an edge case where the UI would not show them as updated
2024-09-30 17:27:50 +10:00
Sam 4b21eb7974
FEATURE: basic support for GPT-o models (#804)
Caveats

- No streaming, by design
- No tool support (including no XML tools)
- No vision

Open AI will revamt the model and more of these features may
become available.

This solution is a bit hacky for now
2024-09-17 09:41:00 +10:00
Sam 03eccbe392
FEATURE: Make tool support polymorphic (#798)
Polymorphic RAG means that we will be able to access RAG fragments both from AiPersona and AiCustomTool

In turn this gives us support for richer RAG implementations.
2024-09-16 08:17:17 +10:00
Sam 5b9add0ac8
FEATURE: add a SambaNova LLM provider (#797)
Note, at the moment the context window is quite small, it is
mainly useful as a helper backend or hyde generator
2024-09-12 11:28:08 +10:00
Sam 36ce88f356
FIX: support case insensitive setting lookup (#795) 2024-09-10 15:21:03 +10:00
Sam a48acc894a
FEATURE: more accurate and faster titles (#791)
Previously we waited 1 minute before automatically titling PMs

The new change introduces adding a title immediately after the the
llm replies

Prompt was also modified to include the LLM reply in title suggestion.

This helps situation like:

user: tell me a joke
llm: a very funy joke about horses

Then the title would be "A Funny Horse Joke"

Specs already covered some auto title logic, amended to also
catch the new message bus message we have been sending.
2024-09-03 15:52:20 +10:00
Roman Rizzi db5cbfb148
FIX: Bail earlier when a chat thread has no messages (#789) 2024-08-30 17:17:14 -03:00
Roman Rizzi ed97827f49
FIX: Correctly display errors when parent module needs to be disabled first (#788)
* FIX: Correctly display errors when parent module needs to be disabled first

* Update spec/configuration/llm_validator_spec.rb

Co-authored-by: Penar Musaraj <pmusaraj@gmail.com>

---------

Co-authored-by: Penar Musaraj <pmusaraj@gmail.com>
2024-08-30 17:16:11 -03:00
Sam 584753cf60
FIX: we were never reindexing old content (#786)
* FIX: we were never reindexing old content

Embedding backfill contains logic for searching for old content
change and then backfilling.

Unfortunately it was excluding all topics that had embedding
unconditionally, leading to no backfill ever happening.


This change adds a test and ensures we backfill.

* over select results, this ensures we will be more likely to find
ai results when filtered
2024-08-30 14:37:55 +10:00
Sam eee8e72756
FEATURE: API scope for semantic search (#785)
The new API scope allows restricting access to semantic search
only.
2024-08-30 09:35:20 +10:00
Sam 41054c4fb8
FEATURE: improve site setting search (#780)
This improves the site setting search so it performs a somewhat
fuzzy match.

Previously it did not handle seperators such as "space" and a
term such as "min_post_length" would not find "min_first_post_length"

A more liberal search algorithm makes it easier to the AI to
navigate settings.

* Minor fix, {{and parameter.enum parameter.enum.length}} is non
obviously broken.


If parameter.enum is a tracked array it will return the object
cause embers and helper implementation.

This corrects an issue where enum keeps on selecting itself by
mistake.
2024-08-29 16:05:38 +10:00
Rafael dos Santos Silva a08d168740
FEATURE: Initial support for seeded LLMs (#756) 2024-08-28 15:57:58 -03:00
Sam 0687ec75c3
FEATURE: allow embedding based search without hyde (#777)
This allows callers of embedding based search to bypass hyde.

Hyde will expand the search term using an LLM, but if an LLM is
performing the search we can skip this expansion.

It also introduced some tests for the controller which we did not have
2024-08-28 14:17:34 +10:00
Roman Rizzi c6aeabbfc0
FIX: Malformed message in systemless + inline img scenario (#771) 2024-08-23 16:41:57 -03:00
Roman Rizzi eac83eb619
FIX: Triage's search_for_text should be case-insensitive (#767) 2024-08-22 18:32:42 -03:00
Roman Rizzi 64641b6175
FEATURE: LLM Triage support for systemless models. (#757)
* FEATURE: LLM Triage support for systemless models.

This change adds support for OSS models without support for system messages. LlmTriage's system message field is no longer mandatory. We now send the post contents in a separate user message.

* Models using Ollama can also disable system prompts
2024-08-21 11:41:55 -03:00
Sam 97fc822cb6
FEATURE: Allow specific groups access to summary feature on PMs (#760)
New `ai_pm_summarization_allowed_groups` can be used to allow
visibility of the summarization feature on PMs.

This can be useful on forums where a lot of communication happens
inside PMs.
2024-08-21 07:58:24 +10:00
Roman Rizzi f789d3ee96
FIX: Triage-flagged posts didn't have a score. (#752)
The score will contain the LLM result, and make sure the flag isn't displayed when a minimum score threshold is present.
2024-08-14 15:54:09 -03:00
Keegan George f72ab12761
DEV: Clearly separate post/composer helper settings (#747) 2024-08-12 15:40:23 -07:00
Sam cf1e15ef12
FIX: gemini 0801 tool calls (#748)
Gemini experimental model requires tool_config.

Previously defaults would apply.

This corrects prompts containing multiple tools on gemini.
2024-08-12 16:10:16 +10:00
Keegan George 0be292f247
FIX: `auto_image_caption` not always present for current user. (#746) 2024-08-08 13:37:26 -07:00
Rafael dos Santos Silva 1686a8a683
DEV: Move to single table per embeddings type (#561)
Also move us to halfvecs for speed and disk usage gains
2024-08-08 11:55:20 -03:00
Roman Rizzi 20efc9285e
FIX: Correctly save provider-specific params for new models. (#744)
Creating a new model, either manually or from presets, doesn't initialize the `provider_params` object, meaning their custom params won't persist.

Additionally, this change adds some validations for Bedrock params, which are mandatory, and a clear message when a completion fails because we cannot build the URL.
2024-08-07 16:08:56 -03:00
Rafael dos Santos Silva 3b5245dc54
FIX: Handle nil reply_to_post in AI Bot event handler (#743)
Somehow it's possible to have a nil `post.reply_to_post` with
a non-nil `post.reply_to_post_number`.
2024-08-07 14:22:32 -03:00
Keegan George 2ff3fe3a9f
UX: Use stacked line chart for post sentiment (#737) 2024-08-02 14:23:29 -07:00
Sam 948cf893a9
FIX: Add tool support to open ai compatible dialect and vllm (#734)
* FIX: Add tool support to open ai compatible dialect and vllm

Automatic tools are in progress in vllm see: https://github.com/vllm-project/vllm/pull/5649

Even when they are supported, initial support will be uneven, only some models have native tool support
notably mistral which has some special tokens for tool support.

After the above PR lands in vllm we will still need to swap to
XML based tools on models without native tool support.

* fix specs
2024-08-02 09:52:33 -03:00
Rafael dos Santos Silva 7dc0a2a20a
DEV: Log error responses on Gemini / Cloudflare embeddings requests (#736) 2024-08-01 17:25:24 -03:00
Roman Rizzi bed044448c
DEV: Remove old code now that features rely on LlmModels. (#729)
* DEV: Remove old code now that features rely on LlmModels.

* Hide old settings and migrate persona llm overrides

* Remove shadowing special URL + seeding code. Use srv:// prefix instead.
2024-07-30 13:44:57 -03:00
Roman Rizzi 5c196bca89
FEATURE: Track if a model can do vision in the llm_models table (#725)
* FEATURE: Track if a model can do vision in the llm_models table

* Data migration
2024-07-24 16:29:47 -03:00
Rafael dos Santos Silva 3502f0f1cd
FEATURE: GPT4o Tokenizer (#721) 2024-07-22 15:26:14 -03:00
Roman Rizzi f328b81c78
FIX: Make sure custom tool enums follow json-schema. (#718)
Enums didn't work as expected because we the dialect couldn't translate
them correctly. It doesn't understand what "enum_values" is.
2024-07-16 14:23:17 -03:00
Roman Rizzi 0a8195242b
FIX: Limit system message size to 60% of available tokens. (#714)
Using RAG fragments can lead to considerably big system messages, which becomes problematic when models have a smaller context window.

Before this change, we only look at the rest of the conversation to make sure we don't surpass the limit, which could lead to two unwanted scenarios when having large system messages:

All other messages are excluded due to size.
The system message already exceeds the limit.

As a result, I'm putting a hard-limit of 60% of available tokens. We don't want to aggresively truncate because if rag fragments are included, the system message contains a lot of context to improve the model response, but we also want to make room for the recent messages in the conversation.
2024-07-12 15:09:01 -03:00
PangBo 4ebbdc043e
fix: locale handling in assistant.rb (#705) 2024-07-05 11:16:09 +02:00
Roman Rizzi 442681a3d3
FIX: Mixtral models have system role support. (#703)
Using assistant role for system produces an error because
they expect alternating roles like user/assistant/user and so on.
Prompts cannot start with the assistant role.
2024-07-04 13:23:03 -03:00
Keegan George eab2f74b58
DEV: Use site locale for composer helper translations (#698) 2024-07-04 08:23:37 -07:00
Sam 1320eed9b2
FEATURE: move summary to use llm_model (#699)
This allows summary to use the new LLM models and migrates of API key based model selection

Claude 3.5 etc... all work now. 

---------

Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
2024-07-04 10:48:18 +10:00
Roman Rizzi fc081d9da6
FIX: Restore ability to fold summaries, which was accidentally removed (#700) 2024-07-03 18:10:31 -03:00
Keegan George 1b0ba9197c
DEV: Add summarization logic from core (#658) 2024-07-02 08:51:59 -07:00
Sam b671ffe7fa
FIX: info not working, not suppressing hidden tags from report (#696)
2 small fixes

1. The info button was not properly working post refactor
2. Suppress any secured tags from report input
2024-07-02 16:38:33 +10:00
Rafael dos Santos Silva a708d4dfa2
FIX: Use base64 encoded images in AI Image Caption via LLaVa (#693)
* FIX: Use base64 encoded images in AI Image Caption via LLaVa

This fixed a regression introduced in #646 where we started sending
schemaless URLs for our LLaVa service, which doesn't handle it well.

Moving to base64 encoded images solves:

- The service needing to download images
  Now the service running LLaVa doesn't need internet access

- Secure uploads compat
  Every image is treated the same, less branching for secure uploads

- Image Size problems
  Discourse is now responsible for ensure a max size for images

- Troublesome dev env
  Previously to this commit you would need a dev env that was internet
acessible to use llava image captions
2024-06-27 16:24:44 -03:00
Sam b863ddc94b
FEATURE: custom user defined tools (#677)
Introduces custom AI tools functionality. 

1. Why it was added:
   The PR adds the ability to create, manage, and use custom AI tools within the Discourse AI system. This feature allows for more flexibility and extensibility in the AI capabilities of the platform.

2. What it does:
   - Introduces a new `AiTool` model for storing custom AI tools
   - Adds CRUD (Create, Read, Update, Delete) operations for AI tools
   - Implements a tool runner system for executing custom tool scripts
   - Integrates custom tools with existing AI personas
   - Provides a user interface for managing custom tools in the admin panel

3. Possible use cases:
   - Creating custom tools for specific tasks or integrations (stock quotes, currency conversion etc...)
   - Allowing administrators to add new functionalities to AI assistants without modifying core code
   - Implementing domain-specific tools for particular communities or industries

4. Code structure:
   The PR introduces several new files and modifies existing ones:

   a. Models:
      - `app/models/ai_tool.rb`: Defines the AiTool model
      - `app/serializers/ai_custom_tool_serializer.rb`: Serializer for AI tools

   b. Controllers:
      - `app/controllers/discourse_ai/admin/ai_tools_controller.rb`: Handles CRUD operations for AI tools

   c. Views and Components:
      - New Ember.js components for tool management in the admin interface
      - Updates to existing AI persona management components to support custom tools 

   d. Core functionality:
      - `lib/ai_bot/tool_runner.rb`: Implements the custom tool execution system
      - `lib/ai_bot/tools/custom.rb`: Defines the custom tool class

   e. Routes and configurations:
      - Updates to route configurations to include new AI tool management pages

   f. Migrations:
      - `db/migrate/20240618080148_create_ai_tools.rb`: Creates the ai_tools table

   g. Tests:
      - New test files for AI tool functionality and integration

The PR integrates the custom tools system with the existing AI persona framework, allowing personas to use both built-in and custom tools. It also includes safety measures such as timeouts and HTTP request limits to prevent misuse of custom tools.

Overall, this PR significantly enhances the flexibility and extensibility of the Discourse AI system by allowing administrators to create and manage custom AI tools tailored to their specific needs.

Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-27 17:27:40 +10:00
Sam af4f871096
FIX: never provide tools with invalid UTF-8 strings (#692)
Previous to this change, on truncation we could return invalid
UTF-8 strings to caller

This also allows tools to read up to 30 megs vs the old 4 megs.
2024-06-27 14:06:52 +10:00
Roman Rizzi f622e2644f
FEATURE: Store provider-specific parameters. (#686)
Previously, we stored request parameters like the OpenAI organization and Bedrock's access key and region as site settings. This change stores them in the `llm_models` table instead, letting us drop more settings while also becoming more flexible.
2024-06-25 08:26:30 +10:00
Sam 1d5fa0ce6c
FIX: when creating an llm we were not creating user (#685)
This meant that if you toggle ai user early it surprisingly did
not work.

Also remove safety settings from gemini, it is overly cautious
2024-06-24 09:59:42 +10:00
Roman Rizzi 091dc626e8
FIX: Make sure LlmEnumerator always return value hashes using symbols (#684) 2024-06-21 16:35:31 -03:00
Sam e04a7be122
FEATURE: LLM presets for model creation (#681)
* FEATURE: LLM presets for model creation

Previous to this users needed to look up complicated settings
when setting up models.

This introduces and extensible preset system with Google/OpenAI/Anthropic
presets.

This will cover all the most common LLMs, we can always add more as
we go.

Additionally:

- Proper support for Anthropic Claude Sonnet 3.5
- Stop blurring api keys when navigating away - this made it very complex to reuse keys
2024-06-21 17:32:15 +10:00
Roman Rizzi 558574fa87
DEV: Use LlmModels as options in automation rules (#676) 2024-06-21 08:07:17 +10:00
Rafael dos Santos Silva 714caf34fe
FEATURE: Support for Claude 3.5 Sonnet via AWS Bedrock (#680) 2024-06-20 17:51:46 -03:00
Roman Rizzi 8849caf136
DEV: Transition "Select model" settings to only use LlmModels (#675)
We no longer support the "provider:model" format in the "ai_helper_model" and
"ai_embeddings_semantic_search_hyde_model" settings. We'll migrate existing
values and work with our new data-driven LLM configs from now on.
2024-06-19 18:01:35 -03:00
Sam 0d6d9a6ef5
FEATURE: allow access to private topics if tool permits (#673)
Previously read tool only had access to public topics, this allows
access to all topics user has access to, if admin opts for the option
Also

- Fixes VLLM migration
- Display which llms have bot enabled
2024-06-19 15:49:36 +10:00
Roman Rizzi 8d5f901a67
DEV: Rewire AI bot internals to use LlmModel (#638)
* DRAFT: Create AI Bot users dynamically and support custom LlmModels

* Get user associated to llm_model

* Track enabled bots with attribute

* Don't store bot username. Minor touches to migrate default values in settings

* Handle scenario where vLLM uses a SRV record

* Made 3.5-turbo-16k the default version so we can remove hack
2024-06-18 14:32:14 -03:00
Sam 460f5c4553
FIX: display search correctly, bug when stripping XML (#668)
- Display filtered search correctly, so it is not confusing
- When XML stripping, if a chunk was `<` it would crash
- SQL Helper improved to be better aware of Data Explorer
2024-06-14 15:28:40 +10:00
Sam f642a27f11
FIX: Dall E / Artist broken when tool_details is disabled (#667)
We were missing logic to handle custom_html from tools

This also fixes image generation in chat
2024-06-12 17:58:28 +10:00
Sam 52a7dd2a4b
FEATURE: optional tool detail blocks (#662)
This is a rather huge refactor with 1 new feature (tool details can
be suppressed)

Previously we use the name "Command" to describe "Tools", this unifies
all the internal language and simplifies the code.

We also amended the persona UI to use less DToggles which aligns
with our design guidelines.

Co-authored-by: Martin Brennan <martin@discourse.org>
2024-06-11 18:14:14 +10:00
Sam 875bb04467
FIX: summarize is not working remove for now (#661)
Summarize is not working right, remove it for now.

Also it was specified twice breaking tool calls.
2024-06-08 12:25:30 +10:00
Roman Rizzi 212ee23698
FIX: Use new report color keys defined in discourse/discourse#27240 (#660) 2024-06-07 15:08:06 -03:00
Sam 8b81ff45b8
FIX: switch off native tools on Anthropic Claude Opus (#659)
Native tools do not work well on Opus.

Chain of Thought prompting means it consumes enormous amounts of
tokens and has poor latency.

This commit introduce and XML stripper to remove various chain of
thought XML islands from anthropic prompts when tools are involved.

This mean Opus native tools is now functions (albeit slowly)

From local testing XML just works better now.

Also fixes enum support in Anthropic native tools
2024-06-07 10:52:01 -03:00
Sam 3993c685e1
FEATURE: anthropic function calling (#654)
Adds support for native tool calling (both streaming and non streaming) for Anthropic.

This improves general tool support on the Anthropic models.
2024-06-06 08:34:23 +10:00