Commit Graph

385 Commits

Author SHA1 Message Date
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
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
Sam 834fea672f
FEATURE: improved tooling (#651)
1. New tool to easily find files (and default branch) in a Github repo
2. Improved read tool with clearer params and larger context

* limit can totally mess up the richness semantic search adds, so include the results unconditionally.
2024-05-30 06:33:50 +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
Loïc Guitaut dd4e305ff7
DEV: Update rubocop-discourse to version 3.8.0 (#641) 2024-05-28 11:15:42 +02:00
Sam 309280cbb6
FEATURE: add aspect ratio support to DallE 3 (#647)
DallE 3 supports tall/square and wide images.

This adds support to the 3 variants. (wide / tall / square)
2024-05-28 16:21:40 +10:00
Keegan George dae9d6f14e
FIX: Move image caption group check logic to server side (#645)
* FIX: User groups error before initialization
* DEV: Move group check logic to server side
2024-05-28 10:29:11 +10:00
Roman Rizzi 333b331eb9
FEATURE: Allow deleting custom LLMs. (#643)
This change allows us to delete custom models. It checks if there is no module using them.

It also fixes a bug where the after-create transition wasn't working. While this prevents a model from being saved multiple times, endpoint validations are still needed (will be added in a separate PR).:
2024-05-27 16:44:08 -03:00
Keegan George a1c649965f
FEATURE: Auto image captions (#637) 2024-05-27 10:49:24 -07:00
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
Sam d4116ecfac
FEATURE: Add support for contextualizing a DM to a bot (#627)
This brings the context of the current topic on screen into chat
2024-05-21 17:17:02 +10:00
Sam 232f12eba6
FEATURE: JavaScript evaluation tool (#630)
This is similar to code interpreter by ChatGPT, except that it uses
JavaScript as the execution engine.

Safeguards were added to ensure memory is constrained and evaluation
times out.
2024-05-21 07:57:01 +10:00
Roman Rizzi 1d786fbaaf
FEATURE: Set endpoint credentials directly from LlmModel. (#625)
* 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>
2024-05-16 09:50:22 -03:00
Bianca Nenciu d5e30592f3
FIX: Load categories from search response (#612)
When lazy load categories is enabled, the list of categories does not
have to fetched from the "site.json" endpoint because it is already
returned by "search.json".

This commit reverts commits 5056502 and 3e54697 because iterating over
all pages of categories is not really necessary.
2024-05-14 17:13:25 +03:00
Sam 8eee6893d6
FEATURE: GPT4o support and better auditing (#618)
- 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
2024-05-14 13:28:46 +10:00
Roman Rizzi 8b00c47087
FIX: dialects var was not defined in prod (#617) 2024-05-13 17:28:27 -03:00
Roman Rizzi e22194f321
HACK: Llama3 support for summarization/AI helper. (#616)
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.
2024-05-13 15:54:42 -03:00
Roman Rizzi 62fc7d6ed0
FEATURE: Configurable LLMs. (#606)
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
2024-05-13 12:46:42 -03:00
Rafael dos Santos Silva 5c02b885ea
FEATURE: Llama 3 tokenizer (#615) 2024-05-13 12:45:52 -03:00
Sam 0069256efd
FIX: improve function call parsing (#613)
- support " / ' wrapped values
- coerce integer to integer
- enforce enum at boundary
2024-05-13 19:40:11 +10:00
Sam 61890b667c
FEATURE: search command now support searching in context of user (#610)
This optional feature allows search to be performed in the context
of the user that executed it.

By default we do not allow this behavior cause it means llm gets
access to potentially secure data.
2024-05-10 11:32:34 +10:00
Sam 514823daca
FIX: streaming broken in bedrock when chunks are not aligned (#609)
Also

- Stop caching llm list - this cause llm list in persona to be incorrect
- Add more UI to debug screen so you can properly see raw response
2024-05-09 12:11:50 +10:00
Sam cf34838a09
FIX: context repairs for @mentioned bot (#608)
When the bot is @mentioned, we need to be a lot more careful
about constructing context otherwise bot gets ultra confused.

This changes multiple things:

1. We were omitting all thread first messages (fixed)
2. Include thread title (if available) in context
3. Construct context in a clearer way separating user request from data
2024-05-08 18:44:04 +10:00
Rafael dos Santos Silva ab4544d897
DEV: Mark hypothetical_post_from method public (#607) 2024-05-07 15:17:26 -03:00
Roman Rizzi 4f1a3effe0
REFACTOR: Migrate Vllm/TGI-served models to the OpenAI format. (#588)
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..
2024-05-07 10:02:16 -03:00
Sam ab78d9b597
REFACTOR: Simplify tool invocation by removing bot_user and llm parameters (#603)
* Well, it was quite a journey but now tools have "context" which
can be critical for the stuff they generate

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

* FIX: improve error handling around image generation

- also corrects image markdown and clarifies code

* fix spec
2024-05-07 21:55:46 +10:00
Sam 88c7427fab
FEATURE: allow @mentioning an ai bot in a channel (#602)
if a persona is mentionable and allows chat allow it to be mentioned in a chat channel
2024-05-07 10:30:39 +10:00
Sam 37a2db5223
FIX: uploader not removing app event (#601)
FIX: restricted to mentionabled vs allowed_chat by mistake
2024-05-06 14:42:55 +10:00
Sam e4b326c711
FEATURE: support Chat with AI Persona via a DM (#488)
Add support for chat with AI personas

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

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

No @mention support yet for ai personas in channels, this is future work
2024-05-06 09:49:02 +10:00
Sam 6623928b95
FIX: call after tool calls failing on OpenAI / Gemini (#599)
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
2024-05-01 17:50:58 +10:00
Sam 32b3004ce9
FEATURE: Add Question Consolidator for robust Upload support in Personas (#596)
This commit introduces a new feature for AI Personas called the "Question Consolidator LLM". The purpose of the Question Consolidator is to consolidate a user's latest question into a self-contained, context-rich question before querying the vector database for relevant fragments. This helps improve the quality and relevance of the retrieved fragments.

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

EG:

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

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

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

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

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

Key changes:

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

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

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

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

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

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

It also means you can no longer exclude "just the parent" but
this is a fair compromise.
2024-04-22 16:05:24 +10:00
Sam bd6f5caeac
FEATURE: Stable diffusion 3 support (#582)
- 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
2024-04-19 18:08:16 +10:00