​
代码

from agno.agent import AgentKnowledge
from agno.embedder.fastembed import FastEmbedEmbedder
from agno.vectordb.pgvector import PgVector

embeddings = FastEmbedEmbedder().get_embedding(
    "The quick brown fox jumps over the lazy dog."
)

# 打印嵌入向量及其维度
print(f"Embeddings: {embeddings[:5]}")
print(f"Dimensions: {len(embeddings)}")

# 用例：
knowledge_base = AgentKnowledge(
    vector_db=PgVector(
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
        table_name="qdrant_embeddings",
        embedder=FastEmbedEmbedder(),
    ),
    num_documents=2,
)

​
用法

1

创建虚拟环境

打开 Terminal 并创建一个 python 虚拟环境。

python3 -m venv .venv
source .venv/bin/activate
2

安装库

pip install -U sqlalchemy 'psycopg[binary]' pgvector fastembed agno
3

运行 PgVector

docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql/data/pgdata \
  -v pgvolume:/var/lib/postgresql/data \
  -p 5532:5432 \
  --name pgvector \
  agnohq/pgvector:16
4

运行 Agent

python cookbook/agent_concepts/knowledge/embedders/qdrant_fastembed.py