Commit Graph

446 Commits

Author SHA1 Message Date
Osama Sayegh 831559662e
UX: Automatically detect text direction for AI generated text (#361) 2023-12-15 13:51:47 -03:00
Keegan George 408d9f68eb
FEATURE: Proofread with post AI helper (#359) 2023-12-14 19:30:52 -08:00
Keegan George 74a7ac4a3d
FEATURE: Add custom prompts to post helper options (#355)
* FEATURE: Add custom prompts to post helper options

* 💄Make pretty

* 💄Make pretty!
2023-12-14 13:47:20 -03:00
Krzysztof Kotlarek 6de9b9c274
DEV: Replace deprecated min_trust_to_create_post (#356)
In https://github.com/discourse/discourse/pull/24740, `min_trust_to_create_topic` site setting was replaced by `create_topic_allowed_groups`. This PR replaces the former, deprecated one, with the latter.
2023-12-14 14:07:28 +11:00
Keegan George 64587967c9
DEV: Cook streamed suggestion (#354) 2023-12-13 12:24:22 -08:00
Roman Rizzi 031c2a6b46
Revert "FIX: Recover from Bedrock returning invalid base64 payloads during streaming (#352)" (#353)
This reverts commit ef7d4cc509.
2023-12-12 17:22:44 -03:00
Roman Rizzi ef7d4cc509
FIX: Recover from Bedrock returning invalid base64 payloads during streaming (#352) 2023-12-12 17:06:53 -03:00
Keegan George 6aaf1f002e
FEATURE: Add streaming to post AI helper's explain option (#344)
Co-authored-by: Rafael dos Santos Silva <xfalcox@gmail.com>
Co-authored-by: Roman Rizzi <roman@discourse.org>
2023-12-12 09:28:39 -08:00
Discourse Translator Bot d4357c29c7
Update translations (#350) 2023-12-12 14:24:01 +01:00
Sam 605445831f
FEATURE: try including views/username/likes in search results (#349)
This is somewhat experimental, but the context of likes/view/username
can help the llm find out what content is more important or even
common users that produce great content

This inflates the amount of tokens somewhat, but given it is all numbers
and search columns titles are only included once this is not severe
2023-12-12 12:22:28 +11:00
Roman Rizzi 2798e4c86d
FIX: Custom instructions where missing when generating custom prompt input (#348) 2023-12-11 19:26:56 -03:00
Keegan George a89549919d
FIX: Missing closing `>` in input tag (#347) 2023-12-11 12:09:17 -08:00
Sam a66b1042cc
FEATURE: scale up result count for search depending on model (#346)
We were limiting to 20 results unconditionally cause we had to make
sure search always fit in an 8k context window.

Models such as GPT 3.5 Turbo (16k) and GPT 4 Turbo / Claude 2.1 (over 150k)
allow us to return a lot more results.

This means we have a much richer understanding cause context is far
larger.

This also allows a persona to tweak this number, in some cases admin
may want to be conservative and save on tokens by limiting results

This also tweaks the `limit` param which GPT-4 liked to set to tell
model only to use it when it needs to (and describes default behavior)
2023-12-11 16:54:16 +11:00
Sam 3c9901d43a
FEATURE: implement GPT-4 turbo support (#345)
Keep in mind:

- GPT-4 is only going to be fully released next year - so this hardcodes preview model for now
- Fixes streaming bugs which became a big problem with GPT-4 turbo
- Adds Azure endpoing for turbo as well

Co-authored-by: Martin Brennan <martin@discourse.org>
2023-12-11 14:59:57 +11:00
Sam 6380ebd829
FEATURE: allow personas to provide command options (#331)
Personas now support providing options for commands.

This PR introduces a single option "base_query" for the SearchCommand. When supplied all searches the persona will perform will also include the pre-supplied filter.

This can allow personas to search a subset of the forum (such as documentation)

This system is extensible we can add options to any command trivially.
2023-12-08 08:42:56 +11:00
Rafael dos Santos Silva 381b0d74ca
FIX: Handle truncation in HyDE search (#342) 2023-12-07 10:36:56 -03:00
Roman Rizzi 450ec915d8
FIX: Make FoldContent strategy more resilient when using models with low token count. (#341)
We'll recursively summarize  the content into smaller chunks until we are sure we can concatenate
them without going over the token limit.
2023-12-06 19:00:24 -03:00
Rafael dos Santos Silva c8352f21ce
FIX: Fallback to whole LLM response when XML fail (#340) 2023-12-06 18:58:26 -03:00
Rafael dos Santos Silva 7ac1dbb6b6
FEATURE: Llama2 support in AiHelper (#339) 2023-12-06 17:47:53 -03:00
Rafael dos Santos Silva 252efdf142
FIX: Don't echo prompt back on HF/TGI (#338)
* FIX: Don't echo prompt back on HF/TGI

* teeeeests
2023-12-06 16:06:26 -03:00
Rafael dos Santos Silva d8267d8da0
FIX: Many fixes for huggingface and llama2 inference (#335) 2023-12-06 11:22:42 -03:00
Martin Brennan 24370a9ca6
Revert "FIX: Use Guardian.basic_user instead of new (anon) (#332)" (#337)
This reverts commit a3a1285dc5.

c.f. https://github.com/discourse/discourse/pull/24742
2023-12-06 16:26:43 +10:00
Mal Curtis 525ba801ff
s/Azuer/Azure (#336) 2023-12-06 17:00:10 +11:00
Martin Brennan a3a1285dc5
FIX: Use Guardian.basic_user instead of new (anon) (#332)
c.f. de983796e1b66aa2ab039a4fb6e32cec8a65a098

There will soon be additional login_required checks
for Guardian, and the intent of many checks by automated
systems is better fulfilled by using BasicUser, which
simulates a logged in TL0 forum user, rather than an
anon user.
2023-12-06 12:01:41 +10:00
Jordan Vidrine 92286ad0c4
UX: Add title to button (#334) 2023-12-05 14:33:10 -06:00
Discourse Translator Bot 5f464c7b1b
Update translations (#333) 2023-12-05 14:39:18 +01:00
Rafael dos Santos Silva 71c5077228
FEATURE: User sentiment on profile summary page (#329)
* FEATURE: User sentiment on profile summary page

This introduces a new user stat in a user profile summary page.

It will show either neutral/positive/negative according to the dominant
sentiment in the user last interactions.

The user-stat widget is only rendered for staff.


Co-authored-by: Keegan George <kgeorge13@gmail.com>
2023-12-04 18:17:43 -03:00
Sam c8cd38cdda
FIX: command selector behavior stopped working (#330)
When moving ai-command-selector from gjs to js the underlying
behavior changed, this corrects it and adds a test case.
2023-12-02 14:20:26 +11:00
Roman Rizzi 3bc010b686
FIX: call the right method to summarize with truncation (#328) 2023-12-01 10:17:24 -03:00
Sam 7f36175ad3
FIX: allow selection of persona when list gets too long (#327) 2023-12-01 08:29:10 +11:00
Jarek Radosz f973fafc33
DEV: Update linting (#326) 2023-11-29 23:01:48 +01:00
Discourse Translator Bot 4ccb98fdcd
Update translations (#320) 2023-11-29 10:41:32 +01:00
Sam a0b9fb9721
FIX: explicitly load embedding strategies (#325)
If not, sometimes during tests these constants may not be loaded
leading to flaky tests
2023-11-29 16:36:56 +11:00
Sam 6ddc17fd61
DEV: port directory structure to Zeitwerk (#319)
Previous to this change we relied on explicit loading for a files in Discourse AI.

This had a few downsides:

- Busywork whenever you add a file (an extra require relative)
- We were not keeping to conventions internally ... some places were OpenAI others are OpenAi
- Autoloader did not work which lead to lots of full application broken reloads when developing.

This moves all of DiscourseAI into a Zeitwerk compatible structure.

It also leaves some minimal amount of manual loading (automation - which is loading into an existing namespace that may or may not be there)

To avoid needing /lib/discourse_ai/... we mount a namespace thus we are able to keep /lib pointed at ::DiscourseAi

Various files were renamed to get around zeitwerk rules and minimize usage of custom inflections

Though we can get custom inflections to work it is not worth it, will require a Discourse core patch which means we create a hard dependency.
2023-11-29 15:17:46 +11:00
Kris 0b9947771c
FIX: adjust tag composer input to avoid wrapping (#324) 2023-11-28 17:38:29 -05:00
Rafael dos Santos Silva fd0fb58eca
FEATURE: HuggingFace Text Embeddings Inference compatibility (#323)
* FEATURE: HuggingFace Text Embeddings Inference compatibility

* lint
2023-11-28 17:05:26 -03:00
Roman Rizzi f26adf2cf6
FIX: Use XML tags in generate_titles prompt. (#322)
We must ensure we can isolate titles, and the models sometimes ignore the example we give them.

Additionally, anons can generate HyDE posts, so we need to check if user is nil when attempting to log requests.
2023-11-28 12:52:22 -03:00
Rafael dos Santos Silva 11e531b099
FEATURE: Backfill task for sentiment module (#316)
* FEATURE: Backfill task for sentiment module

* fix join clause
2023-11-28 12:28:36 -03:00
Roman Rizzi 2e7c5f047d
DEV: Don't attempt to update log if completion request fails. (#321)
We already log the request failure when we raise the exception.
2023-11-28 11:15:12 -03:00
Keegan George 02f7b368a1
FIX: Too many requests from single search (#318) 2023-11-27 17:51:42 -08:00
Keegan George c7665e891b
A11Y: Add title attribute to sparkles icon for AI search results (#317) 2023-11-27 14:25:33 -08:00
Keegan George d493880c0a
FIX: Incorrect sort order label appearing when it should not (#315) 2023-11-27 17:27:22 -03:00
Roman Rizzi 775610b1c2
FIX: Chat titler was still using the old code after LLM migration (#314) 2023-11-27 13:03:24 -03:00
Roman Rizzi 54a8dd9556
REFACTOR: Use LLM abstraction in the AI Helper. (#312)
It also removes the need for multiple versions of our seeded prompts per model, further simplifying the code.
2023-11-27 09:33:31 -03:00
Sam 5a4598a7b4
FEATURE: Azure OpenAI support for DALL*E 3 (#313)
* FEATURE: Azure OpenAI support for DALL*E 3

Previous to this there was no way to add an inference endpoint for
DALL*E on Azure cause it requires custom URLs

Also:

- On save, when editing a persona it would revert priority and enabled
- More forgiving parsing in command framework for array function calls
- By default generate HD images - they tend to be a bit better
- Improve DALL*E prompt which was getting very annoying and always echoing what it is about to do
- Add a bit of a sleep between retries on image generation
- Fix error handling in image_command
2023-11-27 13:01:05 +11:00
Sam dff9f33a97
FEATURE: DALL-E-3 persona for image generation (#311)
* FIX: no selected persona should pick first prioritized one

Previously we were looking at `.personaId` but there is only an
id attribute so it failed

* FEATURE: new DALL-E-3 persona

This persona generates images using DALL-E-3 API and is enabled
by default

Keep in mind that we are still waiting on seeds/gen_id so we can
not retain style consistently between turns.

This will change as soon as a new Open AI API provides the missing
parameters

Co-authored-by: Martin Brennan <martin@discourse.org>
2023-11-24 18:08:08 +11:00
Sam 6282b6d21f
FIX: implement tools framework for Anthropic (#307)
Previous to this changeset we used a custom system for tools/command
support for Anthropic.

We defined commands by using !command as a signal to execute it

Following Anthropic Claude 2.1, there is an official supported syntax (beta)
for tools execution.

eg:

```
+      <function_calls>
+      <invoke>
+      <tool_name>image</tool_name>
+      <parameters>
+      <prompts>
+      [
+      "an oil painting",
+      "a cute fluffy orange",
+      "3 apple's",
+      "a cat"
+      ]
+      </prompts>
+      </parameters>
+      </invoke>
+      </function_calls>
```

This implements the spec per Anthropic, it should be stable enough
to also work on other LLMs.

Keep in mind that OpenAI is not impacted here at all, as it has its
own custom system for function calls.

Additionally:

- Fixes the title system prompt so it works with latest Anthropic
- Uses new spec for "system" messages by Anthropic
- Tweak forum helper persona to guide Anthropic a tiny be better

Overall results are pretty awesome and Anthropic Claude performs
really well now on Discourse
2023-11-24 06:39:56 +11:00
Roman Rizzi 419c43592a
FIX: Make summaries more cohesive by tweaking prompt. (#310)
Other changes:

- Don't use Bedrock for non claude models if credentials are set.
- Remove extra sentence from HyDE prompt.
2023-11-23 16:33:37 -03:00
Keegan George df8804afcd
DEV: Only allow semantic search on "Relevance" sort mode (#306) 2023-11-23 11:30:17 -08:00
Roman Rizzi 02efca162e
FIX: Bedrock uses slightly different model names
* Revert "FIX: We don't need to prepend anthropic. to bedrock models (#308)"

This reverts commit 8a01751991.

* FIX: Bedrock uses slightly different model names
2023-11-23 15:49:24 -03:00