14 Commits
Author SHA1 Message Date
Chih-Yu Yeh 66bfe8a95e Chore(wren-ui): record openai generation model used by user (#254)
* record openai generation model used by user

* remove unused comments
2024-05-15 11:20:10 +08:00
Chih-Yu Yehandwilliam chang d75f6d1ed7 allow users to change openai model in launcher (#244)
* ..

* add logs for init_providers

* fix ci

* add openai model url instructions

* fix empty generation model if OPENAI_GENERATION_MODEL is not provided

* Update wren-launcher/utils/docker.go

Co-authored-by: william chang(張仲威) <wwwy3y3@gmail.com>

---------

Co-authored-by: william chang(張仲威) <wwwy3y3@gmail.com>
2024-05-14 08:49:15 +08:00
Chih-Yu Yeh e0fa7dcb91 refine demo site for easier debugging (#174) 2024-04-29 11:23:12 +08:00
william chang(張仲威)andonlyjackfrost 3c4a6f28a6 Feature: support PG connector (#135)
* feat(wren-ui): add new migration file to support pg in project

* feat(wren-ui): add new pg connector

* feat(wren-ui): install required deps to test pg connector

* feat(wren-ui): refactor strategy a bit (put strategy of data sources into different files) and add pg strategy

* feat(wren-ui): add pg support in repository

* feat(wren-ui): support pg in graphql schema

* feat(wren-ui): fix connection reusing issue and add finalization stage for testing

* feat(wren-ui): change to a better file names & structure in tests

* feat(wren-ui): comment out postgres part in docker-compose-dev

* fix(wren-ui): column properties be empty object in pg connector

---------

Co-authored-by: onlyjackfrost <onlyjackfrost@gmail.com>
2024-04-19 19:05:01 +08:00
Chih-Yu Yeh cf02536bb9 Feature/wren ai service/demo lab (#128)
* setup duckdb demo dataset testing

* allow demo to use duckdb demo dataset

* remove debug message

* remove unused command

* update wren-ai-service demo setup and README

* reformat sql, prevent duplicating deployment, update sampledata mdl

* update logger setup and fix preview sql issue

* remove psycopg2

* refine demo setup flow

* revert

* remove unused file

* remove unused dep

* change url

* revert

* add TODO for improvement

* update
2024-04-18 15:51:09 +08:00
william chang(張仲威) 08af071345 feat(wren-launcher): add rc utility and ensure pg_password generated when deploying services 2024-04-16 11:52:55 +08:00
william chang(張仲威) 7d66b68ada feat(wren-launcher): put accounts file into volume, fix file format 2024-04-16 11:52:55 +08:00
william chang(張仲威) a59bafc7f4 feat(wren-launcher): add pg_username & password to accounts file at bootstrap 2024-04-16 11:52:55 +08:00
9507838991 Feature(ai service): refine ask/ask details pipelines (#64)
* allow visualization using one file

* remove default argparse option value

* resolve conflict

* resolve conflict

* resolve conflict

* update setup instructions

* resolve conflict

* resolve conflicts

* resolve conflict

* resolve conflict

* resolve conflict

* add anthropic model pricing

* allow change model for anthropic

* resolve conflict

* resolve conflict

* resovle conflict

* resovle conflict

* resolve conflict

* resolve conflict

* add container:ubuntu

* undo

* resolve conflict

* resolve conflict

* resolve conflict

* resolve conflict

* resolve conflict

* update

* resolve conflict

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* remove unused files

* resolve conflict

* resolve conflict

* generate ddl from mdl for indexing

* resolve conflict

* resolve conflicts

* eval ask with semantic description (#45)

* update make eval-ask

* add semantic description to mdl before eval

* refine

* add model semantic generation

* simplify make command

* print timestamp

* minor update

---------

Co-authored-by: qa <qa@qadeMacBook-Pro.local>
Co-authored-by: ChihYu Yeh <chihyu.jimmy.yeh@gmail.com>
Co-authored-by: Aster Sun <aster.sun@cannerdata.com>

* remove ;

* simplify prompt

* revert topk

* update prompt

* make default top_k for retriever 10

* generate multiple results for ask pipeline

* resolve conflict

* add followup_generation_pipeline

* add logging for ask api results

* fix generate_mdl issue

* fix ask_details error message

* add extra standard package for uvicorn

* refine ask

* fix postprocessor for ask details

* fix preview data

* fix test

* update prompts

* refine prompts for ask and ask details

* fix prompt

* refine prompt

* remove slash at the end of api endpoints

* refine prompt

* add custom semantic run option

* resolve conflict

* fix bugs for tests and eval and restructure eval-ask

* fix trainling slash and add logging

* remove unused code

* restructure eval ask pipeline outputs

* add comments to the eval command

* change generation component argument name

* add try/except to handle other errors that might happen

* change WREN_AI_SERVICE_VERSION to nightly

* fix eval ask_details errors

* add error message to indexing

---------

Co-authored-by: imAsterSun <61279528+imAsterSun@users.noreply.github.com>
Co-authored-by: qa <qa@qadeMacBook-Pro.local>
Co-authored-by: Aster Sun <aster.sun@cannerdata.com>
Co-authored-by: Pao Sheng <paooap.oappao@gmail.com>
2024-04-08 15:44:15 +08:00
Chih-Yu Yeh 69263e6dd9 Chore/docker compose update (#69)
* update docker related settings

* change WREN_AI_SERVICE_PORT default 5555

* add pull_policy, restart condition and update wren-ai-service port

* fix default port for wren-ai-service
2024-04-03 15:57:09 +08:00
william chang(張仲威) 4ff1ae0678 Feature/home api (#41)
* feat(wren-ui): wrenAIAdaptor

* feat(wren-ui): migration file to add thread tables

* feat(wren-ui): ask feature & thread graphql resolver

* feat(wren-ui): thread repository

* feat(wren-ui): finish ask & thread api

* docker-compose for dev

* fix(wren-ui): fix some transformation issues in API

* fix(wren-ui/ask-feature): fix business logics in thread API

* fix(wren-ui): revert some configs back

* feat(wren-ui/ask): add follow-up question support

* support update/delete thread

* feat(wren-ui/ask): finish preview data & show full sql apis

* feat(wren-ui/ask): use allSettle to print error message if a job failed

* feat(wren-ui/ask): remove showsql mutation & put sql into threadResponse.detail

* fix(wren-ui/ask): fix lint issue

* fix(apollo): handle error formating

* error handling

* change of to create in error
2024-04-01 18:19:36 +08:00
Chih-Yu YehandPao Sheng 32cd3df311 Feature/ai service/fix failed sql queries + add error code (#50)
* resolve conflict

* allow visualization using one file

* remove default argparse option value

* resolve conflict

* resolve conflict

* resolve conflict

* update setup instructions

* resolve conflict

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* add anthropic model pricing

* allow change model for anthropic

* resolve conflicts

* resolve conflicts

* remove invalid sql generation results

* WIP: add sql correction

* add sql correction pipeline

* update ai service ci yaml

* update eval

* add instructions for running tests

* add comments for cte_name validation for last step

* use wren-engine api to validate sql instead of wren-engine psql

* simplify testing instructions

* update testing step

* create missing dir

* fix commands

* add WREN_ENGINE_ENDPOINT

* update WREN_ENGINE_ENDPOINT

* add container:ubuntu

* undo

* changed to localhost

* adjust docker network

* test ci

* test ci

* update

* update

* update

* revert

* update

* revert

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* fix bug

* update

* remove contest

* Feature/ai service/add error code (#40)

* resolve conflict

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* resolve conflicts

* refine

* remove unused files

* resolve conflicts

* add error code and post processor to ask details

* add volume for qdrant and WREN_ENGINE_ENDPOINT for wren-ai-service

* add status check for ask service and fix tests

* Update wren-ai-service/tests/services/test_ask_details.py

Co-authored-by: Pao Sheng <paooap.oappao@gmail.com>

* Update wren-ai-service/tests/services/test_ask_details.py

Co-authored-by: Pao Sheng <paooap.oappao@gmail.com>

---------

Co-authored-by: Pao Sheng <paooap.oappao@gmail.com>

---------

Co-authored-by: Pao Sheng <paooap.oappao@gmail.com>
2024-03-28 15:11:30 +08:00
william chang(張仲威) 3234dc218b Feature/wren launcher (#33)
* feat(dockerfile): add standalone option. fix eslint issues at next.config.js

* feat(docker): add docker-compose file

* feat(launcher): init project

* feat(launcher): use docker-compose sdk to run containers

* feat(laucner): wait until checking if CheckWrenAIStarted return without error

* feat(launcher): CheckDockerDaemonRunning

* feat(laucher): format the message

* feat(launcher): fix regex replace api key

* readme
2024-03-25 17:42:20 +08:00
william chang(張仲威) ffbb2c4084 Feature: build wren-ui docker image & docker-compose to start all service we need (#27)
* feat(dockerfile): add standalone option. fix eslint issues at next.config.js

* feat(docker): add docker-compose file

* feat(docker): add QDRANT_HOST

* feat(docker): modify docker-compose to add a bootstrap runner

* feat(docker): bootstrap service

* feat(wren-ui): add dockerfile for wren-ui

* fix(wren-ui): rm docker entry script

* feat(docker): publish ui & bootstrap packages

* feat(docker): remove comment in dockerfile & put up a how to start in readme

* fix(docker): change ai-service port to 80
2024-03-22 16:39:48 +08:00