WrenAI

mirror of https://github.com/Canner/WrenAI.git synced 2026-09-24 23:29:49 +08:00

Files

T

Chih-Yu Yeh af556b0261 feat(wren-ai-service): optimize qdrant for multi users setting (#558 )

* add binary quantization

* allow multi users setting

* user_id backward compatible

* fix test

* fix conflict

* add user_id to indexing

* remove print

* rename user_id to id

* upgrade qdrant to v1.10.1

* update

* allow using qdrant cloud

* update

* enable binary quantization only if embedding model dim >= 1024

* fix tests

* fix test

* revert

* fix mkdir

* simple refactor

* fix

2024-08-05 13:43:01 +08:00

bootstrap

chore(wren-ui): remove unused code (#555 )

2024-07-29 22:04:01 +08:00

.env.ai.example

feat(wren-ai-service): add gpt-4o-mini (#541 )

2024-07-19 10:20:37 +08:00

.env.example

release 0.7.5 (#573 )

2024-08-01 15:47:38 +08:00

docker-compose-dev.yaml

feat(wren-ai-service): optimize qdrant for multi users setting (#558 )

2024-08-05 13:43:01 +08:00

docker-compose.llm.yaml

Chore/ai service/auto deploy at init (#457 )

2024-06-28 15:22:07 +08:00

docker-compose.yaml

feat(wren-ai-service): optimize qdrant for multi users setting (#558 )

2024-08-05 13:43:01 +08:00

README.md

Chore/ai service/auto deploy at init (#457 )

2024-06-28 15:22:07 +08:00

README.md

Service

wren-engine: the engine service. check out example here: wren-engine /example
wren-ai-service: the AI service. check out example here: wren-ai-service docker-compose example
qdrant: the vector store ai service is using.
wren-ui: the UI service.
bootstrap: put required files to volume for engine service.

Volume

Shared data using data volume.

Path structure as following:

/mdl
- *.json (will put sample.json during bootstrap)
accounts
config.properties

Network

Check out Network drivers overview to learn more about bridge network driver.

How to start with OpenAI

copy .env.example to .env.local and modify the OpenAI API key.
start all services: docker-compose --env-file .env.local up -d.
stop all services: docker-compose --env-file .env.local down.

How to start with custom LLM

copy .env.example to .env.local and modify the OpenAI API key.
copy .env.ai.example to .env.ai and fill in necessary information if you would like to use custom LLM.
start all services(with custom LLM): docker-compose -f docker-compose.yaml -f docker-compose.llm.yaml --env-file .env.local --env-file .env.ai up -d.
stop all services(with custom LLM): docker-compose -f docker-compose.yaml -f docker-compose.llm.yaml --env-file .env.local --env-file .env.ai down.

Note: If your port 3000 is occupied, you can modify the HOST_PORT in .env.local.