ben/coze-studio
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: init improvements (#174)

Browse Source
This commit is contained in:
N3ko
2025-07-29 19:02:03 +08:00
committed by GitHub
parent b48c4c2792
commit 8137b0aee5
9 changed files with 133 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docker/.env.example
View File

@@ -90,8 +90,8 @@ export VIKING_DB_MODEL_NAME="" # if vikingdb model name is not set, you need to
# Settings for Embedding
# The Embedding model relied on by knowledge base vectorization does not need to be configured
# if the vector database comes with built-in Embedding functionality (such as VikingDB). Currently,
# Coze Studio supports three access methods: openai, ark, and custom http. Users can simply choose one of them when using
# embedding type: openai / ark / http
# Coze Studio supports three access methods: openai, ark, ollama, and custom http. Users can simply choose one of them when using
# embedding type: openai / ark / ollama / http
export EMBEDDING_TYPE="ark"
# openai embedding
export OPENAI_EMBEDDING_BASE_URL="" # (string) OpenAI base_url
@@ -108,6 +108,10 @@ export ARK_EMBEDDING_AK=""
export ARK_EMBEDDING_DIMS="2048"
export ARK_EMBEDDING_BASE_URL=""
# ollama embedding
export OLLAMA_EMBEDDING_BASE_URL=""
export OLLAMA_EMBEDDING_MODEL=""
export OLLAMA_EMBEDDING_DIMS=""
# http embedding
export HTTP_EMBEDDING_ADDR="http://127.0.0.1:6543"