Commit graph

153 commits

Author SHA1 Message Date
Salman Paracha
976b2eaae0
fixing docs so that GH pages picks up the right CNAME for DNS (#135)
* fixing docs so that GH pages picks up the right CNAME for DNS

* updating workflow to pick CNAME

* making sure to correctly set permissions on the build/html directory

* fixing GH actions issues with CNAME

* updated docker build command to run as local user

* fixed the CNAME issue and udpated GH actions

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-10-07 11:03:02 -07:00
Adil Hafeez
96686dc606
Serialize tool calls for Arch FC (#131)
* Serialize tool calls

* fix int tests
2024-10-07 00:03:25 -07:00
Adil Hafeez
b43f687b85
add files for local development (#133) 2024-10-06 23:10:13 -07:00
Salman Paracha
b60ceb9168
model server build (#127)
* first commit to have model_server not be dependent on Docker

* making changes to fix the docker-compose file for archgw to set DNS_V4 and minor fixes with the build

* additional fixes for model server to be separated out in the build

* additional fixes for model server to be separated out in the build

* fix to get model_server to be built as a separate python process. TODO: fix the embeddings logs after cli completes

* fixing init to pull tempfile using the tempfile python package

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-10-06 18:21:43 -07:00
Salman Paracha
7d21359f5b
added index.html and made minor README.md edits (#130)
* added index.html and made minor README.md edits

* minor fix to the text

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-10-06 17:16:48 -07:00
Shuguang Chen
5c7567584d
Doc Update (#129)
* init update

* Update terminology.rst

* fix the branch to create an index.html, and fix pre-commit issues

* Doc update

* made several changes to the docs after Shuguang's revision

* fixing pre-commit issues

* fixed the reference file to the final prompt config file

* added google analytics

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-10-06 16:54:34 -07:00
Salman Paracha
2a7b95582c
Build arch docs (#128)
* Build arch docs

The following action would build the docs from main

* triggering a push

* updating the command to run on pull request

* fixed bug

* updated documentation workflow to create a gh-pages branch and update it with the latest build

* fixing the deployment option to mick the right folder

* tested that the pages get build via GH actions, and get published appropriately

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-10-06 11:39:22 -07:00
Salman Paracha
af5671290c fixing CNAME for pre-commit 2024-10-06 09:56:56 -07:00
Salman Paracha
91d7e17c06
Create CNAME 2024-10-06 09:34:29 -07:00
Adil Hafeez
2a747df7c0
don't compute embeddings for names and other fixes see description (#126)
* serialize tools - 2

* fix int tests

* fix int test

* fix unit tests
2024-10-05 19:25:16 -07:00
Salman Paracha
0e5ea3d6db
Salmanap/fix config generator (#124)
* fixed environment variables issue with build. Now llm provider access keys are being written correctly

* fixed and verified that keys are being properly set when archgw is booted up

* removing leaf reference to a staged config file. not needed anymore

* minor fixes to get the build in more stable state

* minor fixes based on feedback

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-10-05 10:49:47 -07:00
Adil Hafeez
5ba7db21d0
fix pkg_resources error (#123) 2024-10-04 20:24:08 -07:00
José Ulises Niño Rivera
2a9b9486f3
Clean up Embeddings Store (#121)
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-10-04 19:33:52 -07:00
José Ulises Niño Rivera
10b5c5b42c
[BUG FIX] Add missing chat completions request hint (#116)
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-10-04 19:19:44 -07:00
Adil Hafeez
07ef1af24f
fix embeddings not found bug (#120) 2024-10-04 17:07:59 -07:00
Salman Paracha
701187474f
load_models checks for device before getting the BGE or NLI model loaded in memory. Was defaulting to CPU. And removed gunk for load_sql (#119)
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-10-04 13:09:35 -07:00
José Ulises Niño Rivera
093891b5f8
Remove hardcoded Access Key Envvars (#118)
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-10-04 11:10:59 -07:00
Co Tran
7d38ef9719
Cotran/hallucination integration (#115)
* fix fc integration

* fix integration

* remove file

* Update arch_fc.py

* create model server hallucination detection class
2024-10-04 11:05:25 -07:00
Salman Paracha
dc57f119a0
archgw cli (#117)
* initial commit of the insurange agent demo, with the CLI tool

* committing the cli

* fixed some field descriptions for generate-prompt-targets

* CLI works with buil, up and down commands. Function calling example works stand-alone

* fixed README to install archgw cli

* fixing based on feedback

* fixing based on feedback

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-10-03 18:21:27 -07:00
José Ulises Niño Rivera
af018e5fd8
Remove optional PromptGuards from Stream Context (#113)
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-10-03 12:21:35 -07:00
José Ulises Niño Rivera
8ea917aae5
Add the ability to use LLM Providers from the Arch config (#112)
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-10-03 10:57:01 -07:00
Adil Hafeez
1b57a49c9d
add support for default target (#111)
* add support for default target

* add more fixes
2024-10-02 20:43:16 -07:00
Aayush
c8d0dbec26
change default stat_prefix from ingress_http to arch (#109)
* change default stat_prefix from ingress_http to arch

* Update arch/envoy.template.yaml

Co-authored-by: Adil Hafeez <adil@katanemo.com>

---------

Co-authored-by: Adil Hafeez <adil@katanemo.com>
2024-10-02 18:21:33 -07:00
Co Tran
ed50d29ccf
fix fc integration (#110)
* fix fc integration

* fix integration

* remove file

* Update arch_fc.py
2024-10-01 19:20:28 -07:00
Aayush
f0fb4a48cd
change root to config in config_generator as well as remove old line 17 from function calling docker compose (#108) 2024-10-01 15:40:55 -07:00
Adil Hafeez
0c572dc862 fix connect_timeout value in ref file 2024-10-01 13:36:25 -07:00
Adil Hafeez
dbb8f87787
update path for arch_config.yaml file (#107) 2024-10-01 13:28:53 -07:00
Co Tran
17a643c410
ArchFC endpoint integration (#94)
* integration

* mopdify docker file

* add params and fix python lint

* fix empty context and tool calls

* address comments

* revert port

* fix bug merge

* fix environment

* fix bug

* fix compose

* fix merge
2024-10-01 12:47:26 -07:00
Adil Hafeez
1a7c1ad0a5
rename archgw_model_sever => model_server (#106) 2024-10-01 11:24:43 -07:00
Salman Paracha
8654d3d5c5
simplify developer getting started experience (#102)
* Fixed build. Now, we have a bare bones version of the docker-compose file with only two services, archgw and archgw-model-server. Tested using CLI

* some pre-commit fixes

* fixed cargo formatting issues

* fixed model server conflict changes

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-10-01 10:02:23 -07:00
Adil Hafeez
41cdef590a
arch schema validator (#105)
* add arch schema validator

* schema validator
2024-10-01 09:22:08 -07:00
Adil Hafeez
15869825e3
add messages in params when making api calls (#104) 2024-10-01 09:14:01 -07:00
Adil Hafeez
f4395d39f9
Fold function_resolver into model_server (#103) 2024-10-01 09:13:50 -07:00
José Ulises Niño Rivera
b0ce5eca93
Rename bolt_config to arch_config (#100)
Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-09-30 18:47:35 -07:00
Adil Hafeez
2207021b9c
remove method type (#101) 2024-09-30 17:59:29 -07:00
José Ulises Niño Rivera
f154bc3741
Remove unnecessary envoy.yaml (#99)
* Remove unnecessary envoy.yaml

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

* more

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

---------

Signed-off-by: José Ulises Niño Rivera <junr03@users.noreply.github.com>
2024-09-30 17:49:25 -07:00
Adil Hafeez
cc35eb0cd7
update config (#93) 2024-09-30 17:49:05 -07:00
Adil Hafeez
4182879717
add precommit check (#97)
* add precommit check

* remove check

* Revert "remove check"

This reverts commit 9987b62b9b.

* fix checks

* fix whitespace errors
2024-09-30 14:54:01 -07:00
Aayush
1e61452310
changes prometheus config target to arch so that data collection works (#98) 2024-09-30 14:35:21 -07:00
Adil Hafeez
bb746e237a
add support for 3b model (#96) 2024-09-30 09:54:58 -07:00
Adil Hafeez
4d7c07a63c update ctx size to 4k 2024-09-29 17:13:05 -07:00
Adil Hafeez
ea86f73605
rename envoyfilter => arch (#91)
* rename envoyfilter => arch

* fix more files

* more fixes

* more renames
2024-09-27 16:41:39 -07:00
Salman Paracha
7168b14ed3
Salmanap/docs v1 push (#92)
* updated model serving, updated the config references, architecture docs and added the llm_provider section

* several documentation changes to improve sections like life_of_a_request, model serving subsystem

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-09-27 15:37:49 -07:00
Adil Hafeez
8a4e11077c update arch-fc parameters 2024-09-27 13:34:10 -07:00
Adil Hafeez
75cf5e5304
Add supported parameter type, validation and tests (#88)
* Add supported parameter type and validation

* make the tools format more compliant with openai

* more updates

* fix more

* fix unit test
2024-09-27 13:33:05 -07:00
Adil Hafeez
59229b8fc9 fix envoy yaml file to use v4 dns resolver for openai 2024-09-27 00:50:27 -07:00
Adil Hafeez
774c389951
add bolt support (#90)
* add support for bolt

* improve logging

* add support for bolt-fc

* fix int tests
2024-09-26 17:47:01 -07:00
Adil Hafeez
e3a835e5d3
expose access logs from envoy (#89) 2024-09-26 16:03:48 -07:00
Salman Paracha
48a2c1800c
V1 docs push (#86)
* updated docs (again)

* updated the LLMs section, prompt processing section and the RAG section of the docs

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>
2024-09-25 23:43:34 -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