doc: fix ob rag doc (#2840)

This commit is contained in:
Aries-ckt
2025-07-14 17:18:10 +08:00
committed by GitHub
parent 3917f8c353
commit 441cb55377
2 changed files with 9 additions and 9 deletions

View File

@@ -1,12 +1,12 @@
# Oceanbase Vector RAG
# OceanBase Vector RAG
In this example, we will show how to use the Oceanbase Vector as in DB-GPT RAG Storage. Using a graph database to implement RAG can, to some extent, alleviate the uncertainty and interpretability issues brought about by vector database retrieval.
In this example, we will show how to use the OceanBase Vector as in DB-GPT RAG Storage. Using a graph database to implement RAG can, to some extent, alleviate the uncertainty and interpretability issues brought about by vector database retrieval.
### Install Dependencies
First, you need to install the `dbgpt Oceanbase Vector storage` library.
First, you need to install the `dbgpt OceanBase Vector storage` library.
```bash
uv sync --all-packages \
@@ -17,19 +17,19 @@ uv sync --all-packages \
--extra "dbgpts"
````
### Prepare Oceanbase Vector
### Prepare OceanBase Vector
Prepare Oceanbase Vector database service, reference[Oceanbase Vector](https://open.oceanbase.com/) .
Prepare OceanBase Vector database service, reference[OceanBase Vector](https://open.oceanbase.com/) .
### TuGraph Configuration
### OceanBase Configuration
Set rag storage variables below in `configs/dbgpt-proxy-openai.toml` file, let DB-GPT know how to connect to Oceanbase Vector.
Set rag storage variables below in `configs/dbgpt-proxy-openai.toml` file, let DB-GPT know how to connect to OceanBase Vector.
```
[rag.storage]
[rag.storage.vector]
type = "Oceanbase"
type = "oceanbase"
uri = "127.0.0.1"
port = "19530"
#username="dbgpt"

View File

@@ -204,7 +204,7 @@ class OceanBaseStore(VectorStoreBase):
"Please install it with `pip install pyobvector`."
)
if vector_store_config.embedding_fn is None:
if embedding_fn is None:
raise ValueError("embedding_fn is required for OceanBaseStore")
super().__init__(