Merge pull request #1203 from chatchat-space/hzg0601-patch-1

Update README.md：lora加载详细步骤参考

README.md

@@ -298,24 +298,13 @@ $ python server/llm_api_shutdown.py --serve all
 
 亦可单独停止一个 FastChat 服务模块，可选 [`all`, `controller`, `model_worker`, `openai_api_server`]
 
-##### 5.1.3 PEFT 加载
+##### 5.1.3 PEFT 加载(包括lora,p-tuning,prefix tuning, prompt tuning,ia等)
 
 本项目基于 FastChat 加载 LLM 服务，故需以 FastChat 加载 PEFT 路径，即保证路径名称里必须有 peft 这个词，配置文件的名字为 adapter_config.json，peft 路径下包含 model.bin 格式的 PEFT 权重。
+详细步骤参考[加载lora微调后模型失效](https://github.com/chatchat-space/Langchain-Chatchat/issues/1130#issuecomment-1685291822)
 
-示例代码如下：
+![image](https://github.com/chatchat-space/Langchain-Chatchat/assets/22924096/4e056c1c-5c4b-4865-a1af-859cd58a625d)
 
-```shell
-PEFT_SHARE_BASE_WEIGHTS=true python3 -m fastchat.serve.multi_model_worker \
-    --model-path /data/chris/peft-llama-dummy-1 \
-    --model-names peft-dummy-1 \
-    --model-path /data/chris/peft-llama-dummy-2 \
-    --model-names peft-dummy-2 \
-    --model-path /data/chris/peft-llama-dummy-3 \
-    --model-names peft-dummy-3 \
-    --num-gpus 2
-```
-
-详见 [FastChat 相关 PR](https://github.com/lm-sys/fastchat/pull/1905#issuecomment-1627801216)
 
 #### 5.2 启动 API 服务
 
@@ -441,6 +430,6 @@ $ python startup.py --all-webui --model-name Qwen-7B-Chat
 
 ## 项目交流群
 
-<img src="img/qr_code_54.jpg" alt="二维码" width="300" height="300" />
+<img src="img/qr_code_55.jpg" alt="二维码" width="300" height="300" />
 
 🎉 langchain-ChatGLM 项目微信交流群，如果你也对本项目感兴趣，欢迎加入群聊参与讨论交流。

configs/model_config.py.example

@@ -114,7 +114,7 @@ kbs_config = {
         "secure": False,
     },
     "pg": {
-        "connection_uri": "postgresql://postgres:postgres@127.0.0.1:5432/langchain_chatglm",
+        "connection_uri": "postgresql://postgres:postgres@127.0.0.1:5432/langchain_chatchat",
     }
 }
 

docs/FAQ.md

@@ -170,3 +170,16 @@ A13: 疑为 chatglm 的 quantization 的问题或 torch 版本差异问题，针
 Q14: 修改配置中路径后，加载 text2vec-large-chinese 依然提示 `WARNING: No sentence-transformers model found with name text2vec-large-chinese. Creating a new one with MEAN pooling.`
 
 A14: 尝试更换 embedding，如 text2vec-base-chinese，请在 [configs/model_config.py](../configs/model_config.py) 文件中，修改 `text2vec-base`参数为本地路径，绝对路径或者相对路径均可
+
+
+---
+
+Q15: 使用pg向量库建表报错
+
+A15: 需要手动安装对应的vector扩展(连接pg执行 CREATE EXTENSION IF NOT EXISTS vector)
+
+---
+
+Q16: pymilvus 连接超时
+
+A16.pymilvus版本需要匹配和milvus对应否则会超时参考pymilvus==2.1.3

docs/docker/vector_db/pg/docker-compose.yml

@@ -2,9 +2,9 @@ version: "3.8"
 services:
  postgresql:
   image: ankane/pgvector:v0.4.1
-  container_name: langchain-chatgml-pg-db
+  container_name: langchain_chatchat-pg-db
   environment:
-      POSTGRES_DB: langchain_chatgml
+      POSTGRES_DB: langchain_chatchat
       POSTGRES_USER: postgres
       POSTGRES_PASSWORD: postgres
   ports:

docs/向量库环境docker.md

@@ -5,3 +5,4 @@
 cd docs/docker/vector_db/milvus
 docker-compose up -d
 ```
+

server/knowledge_base/kb_service/milvus_kb_service.py

@@ -45,10 +45,10 @@ class MilvusKBService(KBService):
     def do_drop_kb(self):
         self.milvus.col.drop()
 
-    def do_search(self, query: str, top_k: int, score_threshold: float, embeddings: Embeddings) -> List[Document]:
+    def do_search(self, query: str, top_k: int, embeddings: Embeddings):
         # todo: support score threshold
         self._load_milvus(embeddings=embeddings)
-        return self.milvus.similarity_search(query, top_k, score_threshold=SCORE_THRESHOLD)
+        return self.milvus.similarity_search_with_score(query, top_k)
 
     def add_doc(self, kb_file: KnowledgeFile):
         """
@@ -76,6 +76,7 @@ class MilvusKBService(KBService):
 if __name__ == '__main__':
     # 测试建表使用
     from server.db.base import Base, engine
+
     Base.metadata.create_all(bind=engine)
     milvusService = MilvusKBService("test")
     milvusService.add_doc(KnowledgeFile("README.md", "test"))

server/knowledge_base/kb_service/pg_kb_service.py

@@ -43,7 +43,7 @@ class PGKBService(KBService):
             '''))
             connect.commit()
 
-    def do_search(self, query: str, top_k: int, score_threshold: float, embeddings: Embeddings) -> List[Document]:
+    def do_search(self, query: str, top_k: int, embeddings: Embeddings):
         # todo: support score threshold
         self._load_pg_vector(embeddings=embeddings)
         return self.pg_vector.similarity_search_with_score(query, top_k)
@@ -76,6 +76,7 @@ class PGKBService(KBService):
 
 if __name__ == '__main__':
     from server.db.base import Base, engine
+
     Base.metadata.create_all(bind=engine)
     pGKBService = PGKBService("test")
     pGKBService.create_kb()