5267ab2d37
feat: retake summary using NousResearch/Hermes-3-Llama-3.1-8B model ( #415 )
...
This feature a new modal endpoint, and a complete new way to build the
summary.
## SummaryBuilder
The summary builder is based on conversational model, where an exchange
between the model and the user is made. This allow more context
inclusion and a better respect of the rules.
It requires an endpoint with OpenAI-like completions endpoint
(/v1/chat/completions)
## vLLM Hermes3
Unlike previous deployment, this one use vLLM, which gives OpenAI-like
completions endpoint out of the box. It could also handle guided JSON
generation, so jsonformer is not needed. But, the model is quite good to
follow JSON schema if asked in the prompt.
## Conversion of long/short into summary builder
The builder is identifying participants, find key subjects, get a
summary for each, then get a quick recap.
The quick recap is used as a short_summary, while the markdown including
the quick recap + key subjects + summaries are used for the
long_summary.
This is why the nextjs component has to be updated, to correctly style
h1 and keep the new line of the markdown.
2024-09-14 02:28:38 +02:00
projects-g
72b22d1005
Update all modal deployments and change seamless configuration due to changes in src repo ( #353 )
...
* update all modal deployments and change seamless configuration due to change in src repo
* add fixture
2024-04-16 21:12:24 +05:30
f7f67521fc
server: try reconcile both tests webrtc and upload with celery worker
2023-12-13 11:25:46 +01:00
99b973f36f
server: fix tests
2023-11-22 14:41:40 +01:00
Sara
a846e38fbd
fix waveform in pipeline
2023-11-17 13:38:32 +01:00
Sara
1fc261a669
try to move waveform to pipeline
2023-11-15 20:30:00 +01:00
e18a7c8d4e
server: correctly save duration, when filewriter is finished
2023-11-11 01:00:09 +01:00
eb76cd9bcd
server/www: rename topic text field to transcript
...
This aleviate the current issue with vercel deployment
2023-11-02 19:59:56 +01:00
4da890b95f
server: add dummy diarization and fixes instanciation
2023-11-02 17:39:21 +01:00
d8a842f099
server: full diarization processor implementation based on gokul app
2023-11-02 17:39:21 +01:00
07c4d080c2
server: refactor with diarization, logic works
2023-11-02 17:39:21 +01:00
projects-g
1d92d43fe0
New summary ( #283 )
...
* handover final summary to Zephyr deployment
* fix display error
* push new summary feature
* fix failing test case
* Added markdown support for final summary
* update UI render issue
* retain sentence tokenizer call
---------
Co-authored-by: Koper <andreas@monadical.com >
2023-10-13 22:53:29 +05:30
4e40cc511a
server: create fixture for starting the server, and always close server even if one test fail
2023-10-13 15:01:58 +02:00
Koper
149342f854
Fix unit tests
2023-10-13 10:42:52 +01:00
projects-g
6a43297309
Translation enhancements ( #247 )
2023-09-26 19:49:54 +05:30
Gokul Mohanarangan
0b00881ce4
update tests: LLM mock to return LLM TITLE for all cases
2023-09-25 10:22:41 +05:30
2b9eef6131
server: use mp3 as default for audio storage
...
Closes #223
2023-09-13 17:26:03 +02:00
projects-g
9fe261406c
Feature additions ( #210 )
...
* initial
* add LLM features
* update LLM logic
* update llm functions: change control flow
* add generation config
* update return types
* update processors and tests
* update rtc_offer
* revert new title processor change
* fix unit tests
* add comments and fix HTTP 500
* adjust prompt
* test with reflector app
* revert new event for final title
* update
* move onus onto processors
* move onus onto processors
* stash
* add provision for gen config
* dynamically pack the LLM input using context length
* tune final summary params
* update consolidated class structures
* update consolidated class structures
* update precommit
* add broadcast processors
* working baseline
* Organize LLMParams
* minor fixes
* minor fixes
* minor fixes
* fix unit tests
* fix unit tests
* fix unit tests
* update tests
* update tests
* edit pipeline response events
* update summary return types
* configure tests
* alembic db migration
* change LLM response flow
* edit main llm functions
* edit main llm functions
* change llm name and gen cf
* Update transcript_topic_detector.py
* PR review comments
* checkpoint before db event migration
* update DB migration of past events
* update DB migration of past events
* edit LLM classes
* Delete unwanted file
* remove List typing
* remove List typing
* update oobabooga API call
* topic enhancements
* update UI event handling
* move ensure_casing to llm base
* update tests
* update tests
2023-09-13 11:26:08 +05:30
68dce235ec
server: pass source and target language from api to pipeline
2023-08-29 11:16:23 +02:00
5c9adb2664
server: fixes tests
2023-08-18 10:23:15 +02:00
f26b6d4621
Merge branch 'main' into feat-user-auth-fief
2023-08-18 10:20:44 +02:00
Gokul Mohanarangan
b08724a191
correct schema typing from str to dict
2023-08-17 20:57:31 +05:30
Gokul Mohanarangan
a98a9853be
PR review comments
2023-08-17 14:42:45 +05:30
Gokul Mohanarangan
17b850951a
pull from main
2023-08-17 09:38:35 +05:30
Gokul Mohanarangan
eb13a7bd64
make schema optional argument
2023-08-17 09:23:14 +05:30
e12f9afe7b
server: implement user authentication (none by default)
2023-08-16 17:24:05 +02:00
a809e5e734
server: implement wav/mp3 audio download
...
If set, will save audio transcription to disk.
MP3 conversion is on-request, but cached to disk as well only if it is successfull.
Closes #148
2023-08-16 09:34:26 +02:00
Mathieu Virbel
26e34aec2d
server: ensure transcript status model is updated + tests
2023-08-09 11:23:28 +02:00
Mathieu Virbel
a9e0c9aa03
server: implement status update in model and websocket
2023-08-09 11:21:48 +02:00
Mathieu Virbel
7f807c8f5f
server: implement FINAL_SUMMARY for websocket + update tests and fix flush
2023-08-08 19:32:20 +02:00
Mathieu Virbel
96f52c631a
api: implement first server API + tests
2023-08-04 20:06:43 +02:00
