Commit Graph

127 Commits

Author SHA1 Message Date
Sam 7ca21cc329
FEATURE: first class support for OpenRouter (#1011)
* FEATURE: first class support for OpenRouter

This new implementation supports picking quantization and provider pref

Also:

- Improve logging for summary generation
- Improve error message when contacting LLMs fails

* Better support for full screen artifacts on iPad

Support back button to close full screen
2024-12-10 05:59:19 +11:00
Roman Rizzi 085dde7042
FEATURE: Select stop sequences from triage script (#1010) 2024-12-06 11:13:47 -03:00
Roman Rizzi 7ebbcd2de3
FIX: Make sure prompt uploads get included in the prompt when triaging (#1008) 2024-12-05 21:04:35 -03:00
Sam a55216773a
FEATURE: Amazon Nova support via bedrock (#997)
Refactor dialect selection and add Nova API support

    Change dialect selection to use llm_model object instead of just provider name
    Add support for Amazon Bedrock's Nova API with native tools
    Implement Nova-specific message processing and formatting
    Update specs for Nova and AWS Bedrock endpoints
    Enhance AWS Bedrock support to handle Nova models
    Fix Gemini beta API detection logic
2024-12-06 07:45:58 +11:00
Sam bc0657f478
FEATURE: AI Usage page (#964)
- Added a new admin interface to track AI usage metrics, including tokens, features, and models.
- Introduced a new route `/admin/plugins/discourse-ai/ai-usage` and supporting API endpoint in `AiUsageController`.
- Implemented `AiUsageSerializer` for structuring AI usage data.
- Integrated CSS stylings for charts and tables under `stylesheets/modules/llms/common/usage.scss`.
- Enhanced backend with `AiApiAuditLog` model changes: added `cached_tokens` column  (implemented with OpenAI for now) with relevant DB migration and indexing.
- Created `Report` module for efficient aggregation and filtering of AI usage metrics.
- Updated AI Bot title generation logic to log correctly to user vs bot
- Extended test coverage for the new tracking features, ensuring data consistency and access controls.
2024-11-29 06:26:48 +11:00
Sam d56ed53eb1
FIX: cancel functionality regressed (#938)
The cancel messaging was not floating correctly to the HTTP call leading to impossible to cancel completions 

This is now fully tested as well.
2024-11-21 17:51:45 +11:00
Sam 755b63f31f
FEATURE: Add support for Mistral models (#919)
Adds support for mistral models (pixtral and mistral large now have presets)

Also corrects token accounting in AWS bedrock models
2024-11-19 17:28:09 +11:00
Sam 0d7f353284
FEATURE: AI artifacts (#898)
This is a significant PR that introduces AI Artifacts functionality to the discourse-ai plugin along with several other improvements. Here are the key changes:

1. AI Artifacts System:
   - Adds a new `AiArtifact` model and database migration
   - Allows creation of web artifacts with HTML, CSS, and JavaScript content
   - Introduces security settings (`strict`, `lax`, `disabled`) for controlling artifact execution
   - Implements artifact rendering in iframes with sandbox protection
   - New `CreateArtifact` tool for AI to generate interactive content

2. Tool System Improvements:
   - Adds support for partial tool calls, allowing incremental updates during generation
   - Better handling of tool call states and progress tracking
   - Improved XML tool processing with CDATA support
   - Fixes for tool parameter handling and duplicate invocations

3. LLM Provider Updates:
   - Updates for Anthropic Claude models with correct token limits
   - Adds support for native/XML tool modes in Gemini integration
   - Adds new model configurations including Llama 3.1 models
   - Improvements to streaming response handling

4. UI Enhancements:
   - New artifact viewer component with expand/collapse functionality
   - Security controls for artifact execution (click-to-run in strict mode)
   - Improved dialog and response handling
   - Better error management for tool execution

5. Security Improvements:
   - Sandbox controls for artifact execution
   - Public/private artifact sharing controls
   - Security settings to control artifact behavior
   - CSP and frame-options handling for artifacts

6. Technical Improvements:
   - Better post streaming implementation
   - Improved error handling in completions
   - Better memory management for partial tool calls
   - Enhanced testing coverage

7. Configuration:
   - New site settings for artifact security
   - Extended LLM model configurations
   - Additional tool configuration options

This PR significantly enhances the plugin's capabilities for generating and displaying interactive content while maintaining security and providing flexible configuration options for administrators.
2024-11-19 09:22:39 +11:00
Sam 823e8ef490
FEATURE: partial tool call support for OpenAI and Anthropic (#908)
Implement streaming tool call implementation for Anthropic and Open AI.

When calling:

llm.generate(..., partial_tool_calls: true) do ...
Partials may contain ToolCall instances with partial: true, These tool calls are partially populated with json partially parsed.

So for example when performing a search you may get:

ToolCall(..., {search: "hello" })
ToolCall(..., {search: "hello world" })

The library used to parse json is:

https://github.com/dgraham/json-stream

We use a fork cause we need access to the internal buffer.

This prepares internals to perform partial tool calls, but does not implement it yet.
2024-11-14 06:58:24 +11:00
Sam 9551b1a4d1
FIX: do not strip empty string during stream processing (#911)
Fixes issue in Open AI provider eating newlines and spaces
2024-11-13 07:12:00 +11:00
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
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
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
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
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
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
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 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
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 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 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
Roman Rizzi c6aeabbfc0
FIX: Malformed message in systemless + inline img scenario (#771) 2024-08-23 16:41:57 -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 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
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
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
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
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
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
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
Keegan George 1b0ba9197c
DEV: Add summarization logic from core (#658) 2024-07-02 08:51:59 -07:00
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
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
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
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 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
Sam 564d2de534
FEATURE: Add native Cohere tool support (#655)
Add native Cohere tool support

- Introduce CohereTools class for tool translation and result processing
- Update Command dialect to integrate with CohereTools
- Modify Cohere endpoint to support passing tools and processing tool calls
- Add spec for testing tool triggering with Cohere endpoint
2024-06-04 08:59:15 +10:00
Roman Rizzi bd1490a536
FIX: include_usage is not available in the Azure API. (#648)
Follow-up #618
2024-05-28 16:55:43 -03:00
Sam b487de933d
FEATURE: add support for all vision models (#646)
Previoulsy on GPT-4-vision was supported, change introduces support
for Google/Anthropic and new OpenAI models

Additionally this makes vision work properly in dev environments
cause we sent the encoded payload via prompt vs sending urls
2024-05-28 10:31:15 -03:00
Sam baf88e7cfc
FEATURE: improve logging by including llm name (#640)
Log the language model name when logging api requests
2024-05-27 16:46:01 +10:00
Sam d5c23f01ff
FIX: correct gemini streaming implementation (#632)
This also implements image support and gemini-flash support
2024-05-22 16:35:29 +10:00
Roman Rizzi 3a9080dd14
FEATURE: Test LLM configuration (#634) 2024-05-21 13:35:50 -03:00