merge master

pilot/configs/model_config.py

@@ -25,26 +25,11 @@ LLM_MODEL_CONFIG = {
     "sentence-transforms": os.path.join(MODEL_PATH, "all-MiniLM-L6-v2")
 }
 
-
-VECTOR_SEARCH_TOP_K = 20
-LLM_MODEL = "vicuna-13b"
-LIMIT_MODEL_CONCURRENCY = 5
-MAX_POSITION_EMBEDDINGS = 4096 
-# VICUNA_MODEL_SERVER = "http://121.41.227.141:8000"
-VICUNA_MODEL_SERVER = "http://120.79.27.110:8000"
-
-# Load model config
 ISLOAD_8BIT = True
 ISDEBUG = False
 
 
-DB_SETTINGS = {
-    "user": "root",
-    "password": "aa123456",
-    "host": "127.0.0.1",
-    "port": 3306
-}
-
+VECTOR_SEARCH_TOP_K = 10
 VS_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "vs_store")
 KNOWLEDGE_UPLOAD_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "data")
 KNOWLEDGE_CHUNK_SPLIT_SIZE = 100

pilot/model/adapter.py

@@ -0,0 +1,96 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+from typing import List
+from functools import cache
+
+from transformers import (
+    AutoTokenizer,
+    AutoModelForCausalLM,
+    AutoModel
+)
+
+class BaseLLMAdaper:
+    """The Base class for multi model, in our project.
+    We will support those model, which performance resemble ChatGPT  """
+
+    def match(self, model_path: str):
+        return True
+
+    def loader(self, model_path: str, from_pretrained_kwargs: dict):
+        tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
+        model = AutoModelForCausalLM.from_pretrained(
+            model_path, low_cpu_mem_usage=True, **from_pretrained_kwargs
+        )
+        return model, tokenizer
+
+
+llm_model_adapters: List[BaseLLMAdaper] = []
+
+# Register llm models to adapters, by this we can use multi models.
+def register_llm_model_adapters(cls):
+    """Register a llm model adapter."""
+    llm_model_adapters.append(cls())
+
+
+@cache
+def get_llm_model_adapter(model_path: str) -> BaseLLMAdaper:
+    for adapter in llm_model_adapters:
+        if adapter.match(model_path):
+            return adapter
+    
+    raise ValueError(f"Invalid model adapter for {model_path}")
+
+
+# TODO support cpu? for practise we support gpt4all or chatglm-6b-int4?
+
+class VicunaLLMAdapater(BaseLLMAdaper):
+    """Vicuna Adapter """
+    def match(self, model_path: str):
+        return "vicuna" in model_path 
+
+    def loader(self, model_path: str, from_pretrained_kwagrs: dict):
+        tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
+        model = AutoModelForCausalLM.from_pretrained(
+            model_path,
+            low_cpu_mem_usage=True,
+            **from_pretrained_kwagrs
+        )
+        return model, tokenizer
+
+class ChatGLMAdapater(BaseLLMAdaper):
+    """LLM Adatpter for THUDM/chatglm-6b"""
+    def match(self, model_path: str):
+        return "chatglm" in model_path
+    
+    def loader(self, model_path: str, from_pretrained_kwargs: dict):
+        tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+        model = AutoModel.from_pretrained(
+            model_path, trust_remote_code=True, **from_pretrained_kwargs
+        ).half().cuda()
+        return model, tokenizer
+
+class KoalaLLMAdapter(BaseLLMAdaper):
+    """Koala LLM Adapter which Based LLaMA """
+    def match(self, model_path: str):
+        return "koala" in model_path
+    
+
+class RWKV4LLMAdapter(BaseLLMAdaper):
+    """LLM Adapter for RwKv4 """
+    def match(self, model_path: str):
+        return "RWKV-4" in model_path
+    
+    def loader(self, model_path: str, from_pretrained_kwargs: dict):
+        # TODO
+        pass
+
+class GPT4AllAdapter(BaseLLMAdaper):
+    """A light version for someone who want practise LLM use laptop."""
+    def match(self, model_path: str):
+        return "gpt4all" in model_path
+
+
+register_llm_model_adapters(VicunaLLMAdapater)
+# TODO Default support vicuna, other model need to tests and Evaluate
+
+register_llm_model_adapters(BaseLLMAdaper)

pilot/server/webserver.py

@@ -19,7 +19,7 @@ from langchain import PromptTemplate
 ROOT_PATH = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 sys.path.append(ROOT_PATH)
 
-from pilot.configs.model_config import DB_SETTINGS, KNOWLEDGE_UPLOAD_ROOT_PATH, LLM_MODEL_CONFIG, VECTOR_SEARCH_TOP_K
+from pilot.configs.model_config import KNOWLEDGE_UPLOAD_ROOT_PATH, LLM_MODEL_CONFIG, VECTOR_SEARCH_TOP_K
 from pilot.server.vectordb_qa import KnownLedgeBaseQA
 from pilot.connections.mysql import MySQLOperator
 from pilot.source_embedding.knowledge_embedding import KnowledgeEmbedding
@@ -440,7 +440,7 @@ def build_single_model_ui():
     notice_markdown = """
     # DB-GPT
     
-    [DB-GPT](https://github.com/csunny/DB-GPT) 是一个实验性的开源应用程序，它基于[FastChat](https://github.com/lm-sys/FastChat)，并使用vicuna-13b作为基础模型。此外，此程序结合了langchain和llama-index基于现有知识库进行In-Context Learning来对其进行数据库相关知识的增强。它可以进行SQL生成、SQL诊断、数据库知识问答等一系列的工作。 总的来说，它是一个用于数据库的复杂且创新的AI工具。如果您对如何在工作中使用或实施DB-GPT有任何具体问题，请联系我, 我会尽力提供帮助, 同时也欢迎大家参与到项目建设中, 做一些有趣的事情。 
+    [DB-GPT](https://github.com/csunny/DB-GPT) 是一个开源的以数据库为基础的GPT实验项目，使用本地化的GPT大模型与您的数据和环境进行交互，无数据泄露风险，100% 私密，100% 安全。 
     """
     learn_more_markdown = """ 
         ### Licence
@@ -641,7 +641,6 @@ if __name__ == "__main__":
     cfg = Config()
 
     # dbs = get_database_list()
-
     cfg.set_plugins(scan_plugins(cfg, cfg.debug_mode))
 
     # 加载插件可执行命令

pilot/vector_store/file_loader.py

@@ -48,7 +48,7 @@ class KnownLedge2Vector:
             # vector_store.add_documents(documents=documents)
         else:
             documents = self.load_knownlege()
-            # reinit
+            # reinit 
             vector_store = Chroma.from_documents(documents=documents, 
                                                  embedding=self.embeddings,
                                                  persist_directory=persist_dir)