mirror of
https://github.com/RYDE-WORK/Langchain-Chatchat.git
synced 2026-01-31 19:33:26 +08:00
3acbf4d5d1
* close #1172: 给webui_page/utils添加一些log信息，方便定位错误 * 修复：重建知识库时页面未实时显示进度 * skip model_worker running when using online model api such as chatgpt * 修改知识库管理相关内容: 1.KnowledgeFileModel增加3个字段：file_mtime(文件修改时间),file_size(文件大小),custom_docs(是否使用自定义docs)。为后面比对上传文件做准备。 2.给所有String字段加上长度，防止mysql建表错误(pr#1177) 3.统一[faiss/milvus/pgvector]_kb_service.add_doc接口，使其支持自定义docs 4.为faiss_kb_service增加一些方法，便于调用 5.为KnowledgeFile增加一些方法，便于获取文件信息，缓存file2text的结果。 * 修复/chat/fastchat无法流式输出的问题 * 新增功能： 1、KnowledgeFileModel增加"docs_count"字段，代表该文件加载到向量库中的Document数量，并在WEBUI中进行展示。 2、重建知识库`python init_database.py --recreate-vs`支持多线程。 其它： 统一代码中知识库相关函数用词：file代表一个文件名称或路径，doc代表langchain加载后的Document。部分与API接口有关或含义重叠的函数暂未修改。 --------- Co-authored-by: liunux4odoo <liunux@qq.com>, hongkong9771
80 lines
3.2 KiB
Python
80 lines
3.2 KiB
Python
from typing import List
|
|
|
|
from langchain.embeddings.base import Embeddings
|
|
from langchain.schema import Document
|
|
from langchain.vectorstores import PGVector
|
|
from langchain.vectorstores.pgvector import DistanceStrategy
|
|
from sqlalchemy import text
|
|
|
|
from configs.model_config import EMBEDDING_DEVICE, kbs_config
|
|
from server.knowledge_base.kb_service.base import SupportedVSType, KBService, EmbeddingsFunAdapter, \
|
|
score_threshold_process
|
|
from server.knowledge_base.utils import load_embeddings, KnowledgeFile
|
|
|
|
|
|
class PGKBService(KBService):
|
|
pg_vector: PGVector
|
|
|
|
def _load_pg_vector(self, embedding_device: str = EMBEDDING_DEVICE, embeddings: Embeddings = None):
|
|
_embeddings = embeddings
|
|
if _embeddings is None:
|
|
_embeddings = load_embeddings(self.embed_model, embedding_device)
|
|
self.pg_vector = PGVector(embedding_function=EmbeddingsFunAdapter(_embeddings),
|
|
collection_name=self.kb_name,
|
|
distance_strategy=DistanceStrategy.EUCLIDEAN,
|
|
connection_string=kbs_config.get("pg").get("connection_uri"))
|
|
|
|
def do_init(self):
|
|
self._load_pg_vector()
|
|
|
|
def do_create_kb(self):
|
|
pass
|
|
|
|
def vs_type(self) -> str:
|
|
return SupportedVSType.PG
|
|
|
|
def do_drop_kb(self):
|
|
with self.pg_vector.connect() as connect:
|
|
connect.execute(text(f'''
|
|
-- 删除 langchain_pg_embedding 表中关联到 langchain_pg_collection 表中 的记录
|
|
DELETE FROM langchain_pg_embedding
|
|
WHERE collection_id IN (
|
|
SELECT uuid FROM langchain_pg_collection WHERE name = '{self.kb_name}'
|
|
);
|
|
-- 删除 langchain_pg_collection 表中 记录
|
|
DELETE FROM langchain_pg_collection WHERE name = '{self.kb_name}';
|
|
'''))
|
|
connect.commit()
|
|
|
|
def do_search(self, query: str, top_k: int, score_threshold: float, embeddings: Embeddings):
|
|
self._load_pg_vector(embeddings=embeddings)
|
|
return score_threshold_process(score_threshold, top_k,
|
|
self.pg_vector.similarity_search_with_score(query, top_k))
|
|
|
|
def do_add_doc(self, docs: List[Document], embeddings: Embeddings, **kwargs):
|
|
self.pg_vector.add_documents(docs)
|
|
|
|
def do_delete_doc(self, kb_file: KnowledgeFile, **kwargs):
|
|
with self.pg_vector.connect() as connect:
|
|
filepath = kb_file.filepath.replace('\\', '\\\\')
|
|
connect.execute(
|
|
text(
|
|
''' DELETE FROM langchain_pg_embedding WHERE cmetadata::jsonb @> '{"source": "filepath"}'::jsonb;'''.replace(
|
|
"filepath", filepath)))
|
|
connect.commit()
|
|
|
|
def do_clear_vs(self):
|
|
self.pg_vector.delete_collection()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
from server.db.base import Base, engine
|
|
|
|
Base.metadata.create_all(bind=engine)
|
|
pGKBService = PGKBService("test")
|
|
pGKBService.create_kb()
|
|
pGKBService.add_doc(KnowledgeFile("README.md", "test"))
|
|
pGKBService.delete_doc(KnowledgeFile("README.md", "test"))
|
|
pGKBService.drop_kb()
|
|
print(pGKBService.search_docs("如何启动api服务"))
|