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.
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>
* 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
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.
* 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
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
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
* 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
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.
* 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
* 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.
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.
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.
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>
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.
* 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
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.
* 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
- 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
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
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
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
* 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>
- Introduce new support for GPT4o (automation / bot / summary / helper)
- Properly account for token counts on OpenAI models
- Track feature that was used when generating AI completions
- Remove custom llm support for summarization as we need better interfaces to control registration and de-registration
There are still some limitations to which models we can support with the `LlmModel` class. This will enable support for Llama3 while we sort those out.
This PR introduces the concept of "LlmModel" as a new way to quickly add new LLM models without making any code changes. We are releasing this first version and will add incremental improvements, so expect changes.
The AI Bot can't fully take advantage of this feature as users are hard-coded. We'll fix this in a separate PR.s
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
Both endpoints provide OpenAI-compatible servers. The only difference is that Vllm doesn't support passing tools as a separate parameter. Even if the tool param is supported, it ultimately relies on the model's ability to handle native functions, which is not the case with the models we have today.
As a part of this change, we are dropping support for StableBeluga/Llama2 models. They don't have a chat_template, meaning the new API can translate them.
These changes let us remove some of our existing dialects and are a first step in our plan to support any LLM by defining them as data-driven concepts.
I rewrote the "translate" method to use a template method and extracted the tool support strategies into its classes to simplify the code.
Finally, these changes bring support for Ollama when running in dev mode. It only works with Mistral for now, but it will change soon..
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
A recent change meant that llm instance got cached internally, repeat calls
to inference would cache data in Endpoint object leading model to
failures.
Both Gemini and Open AI expect a clean endpoint object cause they
set data.
This amends internals to make sure llm.generate will always operate
on clean objects
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.
For quite a few weeks now, some times, when running function calls
on Anthropic we would get a "stray" - "calls" line.
This has been enormously frustrating!
I have been unable to find the source of the bug so instead decoupled
the implementation and create a very clear "function call normalizer"
This new class is extensively tested and guards against the type of
edge cases we saw pre-normalizer.
This also simplifies the implementation of "endpoint" which no longer
needs to handle all this complex logic.
- Updated AI Bot to only support Gemini 1.5 (used to support 1.0) - 1.0 was removed cause it is not appropriate for Bot usage
- Summaries and automation can now lean on Gemini 1.5 pro
- Amazon added support for Claude 3 Opus, added internal support for it on bedrock
Just having the word JSON can confuse models when we expect them
to deal solely in XML
Instead provide an example of how string arrays should be returned
Technically the tool framework supports int arrays and more, but
our current implementation only does string arrays.
Also tune the prompt construction not to give any tips about arrays
if none exist
- Added Cohere Command models (Command, Command Light, Command R, Command R Plus) to the available model list
- Added a new site setting `ai_cohere_api_key` for configuring the Cohere API key
- Implemented a new `DiscourseAi::Completions::Endpoints::Cohere` class to handle interactions with the Cohere API, including:
- Translating request parameters to the Cohere API format
- Parsing Cohere API responses
- Supporting streaming and non-streaming completions
- Supporting "tools" which allow the model to call back to discourse to lookup additional information
- Implemented a new `DiscourseAi::Completions::Dialects::Command` class to translate between the generic Discourse AI prompt format and the Cohere Command format
- Added specs covering the new Cohere endpoint and dialect classes
- Updated `DiscourseAi::AiBot::Bot.guess_model` to map the new Cohere model to the appropriate bot user
In summary, this PR adds support for using the Cohere Command family of models with the Discourse AI plugin. It handles configuring API keys, making requests to the Cohere API, and translating between Discourse's generic prompt format and Cohere's specific format. Thorough test coverage was added for the new functionality.
Open AI just released gpt-4-turbo (with vision)
This change stops using the old preview model and swaps with the
officially released gpt-4-turbo
To come is an implementation of vision.
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>
This PR consolidates the implements new Anthropic Messages interface for Bedrock Claude endpoints and adds support for the new Claude 3 models (haiku, opus, sonnet).
Key changes:
- Renamed `AnthropicMessages` and `Anthropic` endpoint classes into a single `Anthropic` class (ditto for ClaudeMessages -> Claude)
- Updated `AwsBedrock` endpoints to use the new `/messages` API format for all Claude models
- Added `claude-3-haiku`, `claude-3-opus` and `claude-3-sonnet` model support in both Anthropic and AWS Bedrock endpoints
- Updated specs for the new consolidated endpoints and Claude 3 model support
This refactor removes support for old non messages API which has been deprecated by anthropic
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
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
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
* 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
Previous to this fix if a tool call ever streamed a SPACE alone,
we would eat it and ignore it, breaking params
Also fixes some tests to ensure they are actually called :)
The Faraday adapter and `FinalDestionation::HTTP` will protect us from admin-initiated SSRF attacks when interacting with the external services powering this plugin features.:
This PR adds a new feature where you can generate captions for images in the composer using AI.
---------
Co-authored-by: Rafael Silva <xfalcox@gmail.com>
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>
* 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
When bedrock rate limits it returns a 200 BUT also returns a JSON
document with the error.
Previously we had no special case here so we complained about nil
New code properly logs the problem
- Allow users to supply top_p and temperature values, which means people can fine tune randomness
- Fix bad localization string
- Fix bad remapping of max tokens in gemini
- Add support for top_p as a general param to llms
- Amend system prompt so persona stops treating a user as an adversary
* 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
We were not validating input for generate leading to 2 tests not
failing correctly despite functionality being broken.
This ensures that input is validated,and in turn fixes the broken
specs
When you trim a prompt we never want to have a state where there
is a "tool" reply without a corresponding tool call, it makes no
sense
Also
- GPT-4-Turbo is 128k, fix that
- Claude was not preserving username in prompt
- We were throwing away unicode usernames instead of adding to
message
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
* 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>
This PR introduces 3 things:
1. Fake bot that can be used on local so you can test LLMs, to enable on dev use:
SiteSetting.ai_bot_enabled_chat_bots = "fake"
2. More elegant smooth streaming of progress on LLM completion
This leans on JavaScript to buffer and trickle llm results through. It also amends it so the progress dot is much
more consistently rendered
3. It fixes the Claude dialect
Claude needs newlines **exactly** at the right spot, amended so it is happy
---------
Co-authored-by: Martin Brennan <martin@discourse.org>
This allows admins to configure services with multiple backends using DNS SRV records. This PR also adds support for shared secret auth via headers for TEI and vLLM endpoints, so they are inline with the other ones.
* FIX: improve bot behavior
- Provide more information to Gemini context post function execution
- Use system prompts for Claude (fixes Dall E)
- Ensure Assistant is properly separated
- Teach Claude to return arrays in JSON vs XML
Also refactors tests so we do not copy tool preamble everywhere
* System msg is claude-2 only. fix typo
---------
Co-authored-by: Roman Rizzi <rizziromanalejandro@gmail.com>
We thought Azure's latest API version didn't have tool support yet, but I didn't understand it was complaining about a required field in the tool call message.
* 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>
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.
* 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
* FIX: AI helper not working correctly with mixtral
This PR introduces a new function on the generic llm called #generate
This will replace the implementation of completion!
#generate introduces a new way to pass temperature, max_tokens and stop_sequences
Then LLM implementers need to implement #normalize_model_params to
ensure the generic names match the LLM specific endpoint
This also adds temperature and stop_sequences to completion_prompts
this allows for much more robust completion prompts
* port everything over to #generate
* Fix translation
- On anthropic this no longer throws random "This is your translation:"
- On mixtral this actually works
* fix markdown table generation as well
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.
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
This PR adds tool support to available LLMs. We'll buffer tool invocations and return them instead of making users of this service parse the response.
It also adds support for conversation context in the generic prompt. It includes bot messages, user messages, and tool invocations, which we'll trim to make sure it doesn't exceed the prompt limit, then translate them to the correct dialect.
Finally, It adds some buffering when reading chunks to handle cases when streaming is extremely slow.:M
Sam
Rafael dos Santos Silva
Hoa Nguyen
Roman Rizzi
Keegan George
Jarek Radosz