apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-04-29 19:06:34 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
106 commits 499 branches 66 tags 82 MiB
Commit graph

61 commits

Author SHA1 Message Date
Adil Hafeez
e3a835e5d3
expose access logs from envoy (#89) 2024-09-26 16:03:48 -07:00
Adil Hafeez
3511798fa8
Integrate Arch-Function-Calling-1.5B model (#85) 
* add arch support

* add missing file

* e2e tests

* delete old files and fix response

* fmt
 2024-09-25 23:30:50 -07:00
José Ulises Niño Rivera
9ea6bb0d73
Revert "Revert "Add support for multiple LLM Providers (#60)"" (#83) 
* Revert "Revert "Add support for multiple LLM Providers (#60)""

This reverts commit 43d6bc80e9.

* wip

Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>

* Revert "wip"

This reverts commit 7c4dde5d1f.

* fix parameter name

Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>

* force use openai

---------

Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
Co-authored-by: Adil Hafeez <adil@katanemo.com>
 2024-09-25 23:15:17 -07:00
Adil Hafeez
43d6bc80e9 Revert "Add support for multiple LLM Providers (#60)" 
This reverts commit bd8206742a.
 2024-09-25 08:15:22 -07:00
Adil Hafeez
d970b214f4
improve logging of api failure (#79) 2024-09-24 23:56:24 -07:00
José Ulises Niño Rivera
bd8206742a
Add support for multiple LLM Providers (#60) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-09-24 17:13:55 -07:00
Adil Hafeez
87900beddd
Remove OMF (#78) 
* Remove OMF

* remove submodule from github workflow
 2024-09-24 15:18:20 -07:00
Adil Hafeez
2d31aeaa36 fix debug log 2024-09-24 13:45:30 -07:00
Adil Hafeez
dd8c43a392
improve cluster not configured error (#73) 
* improve cluster not configured error

* dont panic

* update format

* Merge branch 'main' into adil/fix_salman_docs
 2024-09-24 13:24:26 -07:00
Adil Hafeez
eff4cd9826
improve response handling (#71) 2024-09-23 22:56:35 -07:00
Co Tran
79b1c5415f
[Kan-103] add support toxic/jailbreak model (#49) 
* add toxic/jailbreak model

* fix path loading model

* fix syntax

* fix bug,lint, format

* fix bug

* formatting

* add parallel + chunking

* fix bug

* working version

* fix onnnx name erorr

* device

* fix jailbreak config

* fix syntax error

* format

* add requirement + cli download for dockerfile

* add task

* add skeleton change for envoy filter for prompt guard

* fix hardware config

* fix bug

* add config changes

* add gitignore

* merge main

* integrate arch-guard with filter

* add hardware config

* nothing

* add hardware config feature

* fix requirement

* fix chat ui

* fix onnx

* fix lint

* remove non intel cpu

* remove onnx

* working version

* modify docker

* fix guard time

* add nvidia support

* remove nvidia

* add gpu

* add gpu

* add gpu support

* add gpu support for compose

* add gpu support for compose

* add gpu support for compose

* add gpu support for compose

* add gpu support for compose

* fix docker file

* fix int test

* correct gpu docker

* upgrad python 10

* fix logits to be gpu compatible

* default to cpu dockerfile

* resolve comments

* fix lint + unused parameters

* fix

* remove eetq install for cpu

* remove deploy gpu

---------

Co-authored-by: Adil Hafeez <adil@katanemo.com>
 2024-09-23 12:07:31 -07:00
Adil Hafeez
233976a568 comment required param check 2024-09-20 15:49:49 -07:00
Adil Hafeez
ca5c9e4824 improve logging 2024-09-20 10:16:58 -07:00
Sampreeth Sarma
941869ad24
fix similarity bug (#63) 2024-09-20 09:49:28 -07:00
Adil Hafeez
97b47c2ab4
Include param default in parameters (#68) 
* Include param default in parameters

* improve default param pr

* fix integration tests
 2024-09-20 09:02:24 -07:00
Adil Hafeez
aa73a5aaae
Update Dockerfile 2024-09-19 20:06:38 -07:00
Adil Hafeez
4438dc7979
remove embeddings config from config (#64) 
* remove embeddings config from config

* remove embedding provider
 2024-09-19 17:49:42 -07:00
José Ulises Niño Rivera
7568507764
Delete unused envoy.yaml file (#65) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-09-19 17:49:26 -07:00
Adil Hafeez
3215d81e58
fix webui url and dependencies (#66) 2024-09-19 17:48:50 -07:00
Adil Hafeez
2cd5ec5adf
use openai standard response in arch-fc and in gradio client (#62) 
* use openai standard response in arch-fc and in gradio client

also fix code bug in usage

* fix int test
 2024-09-19 12:19:14 -07:00
Adil Hafeez
a91fbdbf1c
Add ability to define clusters in config (#61) 2024-09-18 20:03:26 -07:00
Adil Hafeez
215d276acf
send all tools when sending request to arch-fc (#59) 2024-09-18 15:54:40 -07:00
Adil Hafeez
3135ba8eae
add ability to override default values from config (#58) 2024-09-17 22:37:58 -07:00
José Ulises Niño Rivera
9f3c845610
Add ability to stream a response (#50) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-09-17 16:12:41 -07:00
Adil Hafeez
8a265de7c6
Propagate enums from prompt-target to bolt-fc (#56) 2024-09-17 12:03:21 -07:00
Adil Hafeez
63143fbd01
add bolt guard config (#55) 2024-09-17 10:59:50 -07:00
Adil Hafeez
060a0d665e
improve service names (#54) 
- embedding-server => model_server
- public-types => public_types
- chatbot-ui => chatbot_ui
- function-calling => function_calling
 2024-09-17 08:47:35 -07:00
Adil Hafeez
ed329bd419 improve docker build speed 2024-09-16 19:20:27 -07:00
Adil Hafeez
9e50957f22
Improve prompt target intent matching (#51) 2024-09-16 19:20:07 -07:00
José Ulises Niño Rivera
8565462ec4
Resetting instead of resuming (#39) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-09-14 10:58:25 -07:00
José Ulises Niño Rivera
3c5ac65e2a
More idiomatic conversion (#47) 
* More idiomatic conversion

Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>

* errors

Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>

---------

Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-09-11 10:00:25 -07:00
Adil Hafeez
7b5203a2ce
Add function calling support using bolt-fc-1b (#35) 2024-09-10 14:24:46 -07:00
José Ulises Niño Rivera
fdfad87347
Fix wasm load error (#45) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-09-05 16:29:41 -07:00
José Ulises Niño Rivera
dd48689aee
Add Ratelimit on request tokens (#44) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-09-04 17:28:12 -07:00
José Ulises Niño Rivera
d98517f240
Move shared types into their own crate (#41) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-09-04 15:31:05 -07:00
José Ulises Niño Rivera
4dd1f3693e
Add the Ratelimit module (#34) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-08-28 11:11:05 -07:00
José Ulises Niño Rivera
2a4cde950d
Add Ratelimit config (#32) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-08-07 14:15:26 -07:00
Adil Hafeez
445b1ea210
Add support for local llm (mistral 7b) (#31) 2024-08-06 23:40:06 -07:00
José Ulises Niño Rivera
b49fc2f264
Simplify Entity struct (#33) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-08-06 17:04:32 -07:00
Adil Hafeez
6f6454069f
Improve demo experience (#28) 
* Imrpove demo experience
- generate envoy.yaml using jinja2 template

* add todo

* add config file
 2024-07-31 17:13:39 -07:00
Adil Hafeez
51d6213cdd
update open-message-format (#30) 2024-07-31 15:56:13 -07:00
Adil Hafeez
56328bfb16 fix break 2024-07-31 14:43:28 -07:00
Adil Hafeez
9774148c75
Remove top level container and start snake-case for config files (#27) 
t
 2024-07-31 14:05:52 -07:00
José Ulises Niño Rivera
b8ea65d858
Remove unnecessary clones (#26) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
Co-authored-by: Adil Hafeez <adil@katanemo.com>
 2024-07-31 11:48:34 -07:00
José Ulises Niño Rivera
c13682a03b
Clean up imports (#25) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-07-31 11:33:39 -07:00
Adil Hafeez
5ecdf30fdc refactor callout context arm handler code 2024-07-30 18:20:57 -07:00
Adil Hafeez
33f9dd22e6
Add workflow logic for weather forecast demo (#24) 2024-07-30 16:23:23 -07:00
José Ulises Niño Rivera
7ef68eccfb
Improve error handling (#23) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-07-29 12:15:26 -07:00
José Ulises Niño Rivera
a51a467cad
Add initial integration style tests (#20) 
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
 2024-07-25 14:41:36 -07:00
Adil Hafeez
a0abd9c42d
refactor code a bit (#21) 2024-07-24 14:13:18 -07:00