diff --git a/.gitignore b/.gitignore
index 3a4c26b..6bc9886 100644
--- a/.gitignore
+++ b/.gitignore
@@ -15,3 +15,5 @@ tests
*egg-info
build
dist
+package.sh
+local_config.json
\ No newline at end of file
diff --git a/README.md b/README.md
index 57f540c..8853fef 100644
--- a/README.md
+++ b/README.md
@@ -123,60 +123,23 @@ cd codefuse-chatbot
pip install -r requirements.txt
```
-2、基础配置
-
-```bash
-# 修改服务启动的基础配置
-cd configs
-cp model_config.py.example model_config.py
-cp server_config.py.example server_config.py
-
-# model_config#11~12 若需要使用openai接口，openai接口key
-os.environ["OPENAI_API_KEY"] = "sk-xxx"
-# 可自行替换自己需要的api_base_url
-os.environ["API_BASE_URL"] = "https://api.openai.com/v1"
-
-# vi model_config#LLM_MODEL 你需要选择的语言模型
-LLM_MODEL = "gpt-3.5-turbo"
-LLM_MODELs = ["gpt-3.5-turbo"]
-
-# vi model_config#EMBEDDING_MODEL 你需要选择的私有化向量模型
-EMBEDDING_ENGINE = 'model'
-EMBEDDING_MODEL = "text2vec-base"
-
-# vi model_config#embedding_model_dict 修改成你的本地路径，如果能直接连接huggingface则无需修改
-# 若模型地址为：
-model_dir: ~/codefuse-chatbot/embedding_models/shibing624/text2vec-base-chinese
-# 配置如下
-"text2vec-base": "shibing624/text2vec-base-chinese",
-
-# vi server_config#8~14, 推荐采用容器启动服务
-DOCKER_SERVICE = True
-# 是否采用容器沙箱
-SANDBOX_DO_REMOTE = True
-# 是否采用api服务来进行
-NO_REMOTE_API = True
-```
-
-3、启动服务
-
-默认只启动webui相关服务，未启动fastchat（可选）。
-```bash
-# 若需要支撑codellama-34b-int4模型，需要给fastchat打一个补丁
-# cp examples/gptq.py ~/site-packages/fastchat/modules/gptq.py
-# examples/llm_api.py#258 修改为 kwargs={"gptq_wbits": 4},
-
-# start llm-service（可选）
-python examples/llm_api.py
-```
-更多LLM接入方法见[更多细节...](sources/readme_docs/fastchat.md)
-
-
+2、启动服务
```bash
# 完成server_config.py配置后，可一键启动
cd examples
-python start.py
+bash start.sh
+# 开始在页面进行配置即可
```
+
+
+
+
+
## 贡献指南
非常感谢您对 Codefuse 项目感兴趣，我们非常欢迎您对 Codefuse 项目的各种建议、意见（包括批评）、评论和贡献。
diff --git a/README_en.md b/README_en.md
index 1d7e5b9..b5a97bb 100644
--- a/README_en.md
+++ b/README_en.md
@@ -146,57 +146,23 @@ git lfs clone https://huggingface.co/THUDM/chatglm2-6b
git lfs clone https://huggingface.co/shibing624/text2vec-base-chinese
```
-4. Basic Configuration
-
-```bash
-# Modify the basic configuration for service startup
-cd configs
-cp model_config.py.example model_config.py
-cp server_config.py.example server_config.py
-
-# model_config#11~12 If you need to use the openai interface, openai interface key
-os.environ["OPENAI_API_KEY"] = "sk-xxx"
-# You can replace the api_base_url yourself
-os.environ["API_BASE_URL"] = "https://api.openai.com/v1"
-
-# vi model_config#105 You need to choose the language model
-LLM_MODEL = "gpt-3.5-turbo"
-
-# vi model_config#43 You need to choose the vector model
-EMBEDDING_MODEL = "text2vec-base"
-
-# vi model_config#25 Modify to your local path, if you can directly connect to huggingface, no modification is needed
-"text2vec-base": "shibing624/text2vec-base-chinese",
-
-# vi server_config#8~14, it is recommended to start the service using containers.
-DOCKER_SERVICE = True
-# Whether to use container sandboxing is up to your specific requirements and preferences
-SANDBOX_DO_REMOTE = True
-# Whether to use api-service to use chatbot
-NO_REMOTE_API = True
-```
-
-5. Start the Service
-
-By default, only webui related services are started, and fastchat is not started (optional).
-```bash
-# if use codellama-34b-int4, you should replace fastchat's gptq.py
-# cp examples/gptq.py ~/site-packages/fastchat/modules/gptq.py
-# examples/llm_api.py#258 => kwargs={"gptq_wbits": 4},
-
-# start llm-service（可选）
-python examples/llm_api.py
-```
-More details about accessing LLM Moldes[More Details...](sources/readme_docs/fastchat.md)
-
+4. Start the Service
```bash
# After configuring server_config.py, you can start with just one click.
cd examples
-bash start_webui.sh
+bash start.sh
+# you can config your llm model and embedding model
```
+
+
+
+
+## Contribution
Thank you for your interest in the Codefuse project. We warmly welcome any suggestions, opinions (including criticisms), comments, and contributions to the Codefuse project.
Your suggestions, opinions, and comments on Codefuse can be directly submitted through GitHub Issues.
diff --git a/coagent/base_configs/env_config.py b/coagent/base_configs/env_config.py
index e931131..8005dcd 100644
--- a/coagent/base_configs/env_config.py
+++ b/coagent/base_configs/env_config.py
@@ -1,5 +1,6 @@
import os
import platform
+from loguru import logger
system_name = platform.system()
executable_path = os.getcwd()
@@ -7,8 +8,8 @@ executable_path = os.getcwd()
# 日志存储路径
LOG_PATH = os.environ.get("LOG_PATH", None) or os.path.join(executable_path, "logs")
-# 知识库默认存储路径
-SOURCE_PATH = os.environ.get("SOURCE_PATH", None) or os.path.join(executable_path, "sources")
+# # 知识库默认存储路径
+# SOURCE_PATH = os.environ.get("SOURCE_PATH", None) or os.path.join(executable_path, "sources")
# 知识库默认存储路径
KB_ROOT_PATH = os.environ.get("KB_ROOT_PATH", None) or os.path.join(executable_path, "knowledge_base")
@@ -16,8 +17,8 @@ KB_ROOT_PATH = os.environ.get("KB_ROOT_PATH", None) or os.path.join(executable_p
# 代码库默认存储路径
CB_ROOT_PATH = os.environ.get("CB_ROOT_PATH", None) or os.path.join(executable_path, "code_base")
-# nltk 模型存储路径
-NLTK_DATA_PATH = os.environ.get("NLTK_DATA_PATH", None) or os.path.join(executable_path, "nltk_data")
+# # nltk 模型存储路径
+# NLTK_DATA_PATH = os.environ.get("NLTK_DATA_PATH", None) or os.path.join(executable_path, "nltk_data")
# 代码存储路径
JUPYTER_WORK_PATH = os.environ.get("JUPYTER_WORK_PATH", None) or os.path.join(executable_path, "jupyter_work")
@@ -31,8 +32,8 @@ NEBULA_PATH = os.environ.get("NEBULA_PATH", None) or os.path.join(executable_pat
# CHROMA 存储路径
CHROMA_PERSISTENT_PATH = os.environ.get("CHROMA_PERSISTENT_PATH", None) or os.path.join(executable_path, "data/chroma_data")
-for _path in [LOG_PATH, SOURCE_PATH, KB_ROOT_PATH, CB_ROOT_PATH, NLTK_DATA_PATH, JUPYTER_WORK_PATH, WEB_CRAWL_PATH, NEBULA_PATH, CHROMA_PERSISTENT_PATH]:
- if not os.path.exists(_path):
+for _path in [LOG_PATH, KB_ROOT_PATH, CB_ROOT_PATH, JUPYTER_WORK_PATH, WEB_CRAWL_PATH, NEBULA_PATH, CHROMA_PERSISTENT_PATH]:
+ if not os.path.exists(_path) and int(os.environ.get("do_create_dir", True)):
os.makedirs(_path, exist_ok=True)
# 数据库默认存储路径。
diff --git a/coagent/codechat/codebase_handler/codebase_handler.py b/coagent/codechat/codebase_handler/codebase_handler.py
index 2af52c6..601cae1 100644
--- a/coagent/codechat/codebase_handler/codebase_handler.py
+++ b/coagent/codechat/codebase_handler/codebase_handler.py
@@ -101,6 +101,7 @@ class CodeBaseHandler:
# get KG info
if self.nh:
+ time.sleep(10) # aviod nebula staus didn't complete
stat = self.nh.get_stat()
vertices_num, edges_num = stat['vertices'], stat['edges']
else:
diff --git a/coagent/connector/memory_manager.py b/coagent/connector/memory_manager.py
index a7d8436..3ccd698 100644
--- a/coagent/connector/memory_manager.py
+++ b/coagent/connector/memory_manager.py
@@ -310,7 +310,8 @@ class LocalMemoryManager(BaseMemoryManager):
#
save_to_json_file(memory_messages, file_path)
- def load(self, load_dir: str = "./") -> Memory:
+ def load(self, load_dir: str = None) -> Memory:
+ load_dir = load_dir or self.kb_root_path
file_path = os.path.join(load_dir, f"{self.user_name}/{self.unique_name}/{self.memory_type}/converation.jsonl")
uuid_name = "_".join([self.user_name, self.unique_name, self.memory_type])
@@ -398,6 +399,7 @@ class LocalMemoryManager(BaseMemoryManager):
def embedding_retrieval(self, text: str, top_k=1, score_threshold=1.0, user_name: str = "default", **kwargs) -> List[Message]:
if text is None: return []
vb_name = f"{user_name}/{self.unique_name}/{self.memory_type}"
+ # logger.debug(f"vb_name={vb_name}")
vb = KBServiceFactory.get_service(vb_name, "faiss", self.embed_config, self.kb_root_path)
docs = vb.search_docs(text, top_k=top_k, score_threshold=score_threshold)
return [Message(**doc.metadata) for doc, score in docs]
@@ -405,11 +407,13 @@ class LocalMemoryManager(BaseMemoryManager):
def text_retrieval(self, text: str, user_name: str = "default", **kwargs) -> List[Message]:
if text is None: return []
uuid_name = "_".join([user_name, self.unique_name, self.memory_type])
+ # logger.debug(f"uuid_name={uuid_name}")
return self._text_retrieval_from_cache(self.recall_memory_dict[uuid_name].messages, text, score_threshold=0.3, topK=5, **kwargs)
def datetime_retrieval(self, datetime: str, text: str = None, n: int = 5, user_name: str = "default", **kwargs) -> List[Message]:
if datetime is None: return []
uuid_name = "_".join([user_name, self.unique_name, self.memory_type])
+ # logger.debug(f"uuid_name={uuid_name}")
return self._datetime_retrieval_from_cache(self.recall_memory_dict[uuid_name].messages, datetime, text, n, **kwargs)
def _text_retrieval_from_cache(self, messages: List[Message], text: str = None, score_threshold=0.3, topK=5, tag_topK=5, **kwargs) -> List[Message]:
diff --git a/coagent/sandbox/pycodebox.py b/coagent/sandbox/pycodebox.py
index 39a4ab9..b1dc189 100644
--- a/coagent/sandbox/pycodebox.py
+++ b/coagent/sandbox/pycodebox.py
@@ -7,7 +7,7 @@ from websocket import create_connection
from websockets.client import WebSocketClientProtocol, ClientConnection
from websockets.exceptions import ConnectionClosedError
-# from configs.model_config import JUPYTER_WORK_PATH
+from coagent.base_configs.env_config import JUPYTER_WORK_PATH
from .basebox import BaseBox, CodeBoxResponse, CodeBoxStatus
@@ -21,7 +21,7 @@ class PyCodeBox(BaseBox):
remote_ip: str = "http://127.0.0.1",
remote_port: str = "5050",
token: str = "mytoken",
- jupyter_work_path: str = "",
+ jupyter_work_path: str = JUPYTER_WORK_PATH,
do_code_exe: bool = False,
do_remote: bool = False,
do_check_net: bool = True,
@@ -30,7 +30,6 @@ class PyCodeBox(BaseBox):
super().__init__(remote_url, remote_ip, remote_port, token, do_code_exe, do_remote)
self.enter_status = True
self.do_check_net = do_check_net
- self.use_stop = use_stop
self.jupyter_work_path = jupyter_work_path
# asyncio.run(self.astart())
self.start()
diff --git a/coagent/utils/code2doc_util.py b/coagent/utils/code2doc_util.py
index 11cffd4..7e67923 100644
--- a/coagent/utils/code2doc_util.py
+++ b/coagent/utils/code2doc_util.py
@@ -70,7 +70,8 @@ def encode2md(data, md_format):
return md_dict
-method_text_md = '''> {function_name}
+method_text_md = '''
+> {function_name}
| Column Name | Content |
|-----------------|-----------------|
@@ -79,7 +80,8 @@ method_text_md = '''> {function_name}
| Return type | {ReturnType} |
'''
-class_text_md = '''> {code_path}
+class_text_md = '''
+> {code_path}
Bases: {ClassBase}
diff --git a/configs/default_config.py b/configs/default_config.py
index 3d71d89..e375d9e 100644
--- a/configs/default_config.py
+++ b/configs/default_config.py
@@ -22,11 +22,14 @@ JUPYTER_WORK_PATH = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath
WEB_CRAWL_PATH = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "knowledge_base")
# NEBULA_DATA存储路径
NEBULA_PATH = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "data/nebula_data")
-
+# 语言模型存储路径
+LOCAL_LLM_MODEL_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "llm_models")
+# 向量模型存储路径
+LOCAL_EM_MODEL_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "embedding_models")
# CHROMA 存储路径
CHROMA_PERSISTENT_PATH = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "data/chroma_data")
-for _path in [LOG_PATH, SOURCE_PATH, KB_ROOT_PATH, CB_ROOT_PATH, NLTK_DATA_PATH, JUPYTER_WORK_PATH, WEB_CRAWL_PATH, NEBULA_PATH, CHROMA_PERSISTENT_PATH]:
+for _path in [LOG_PATH, SOURCE_PATH, KB_ROOT_PATH, CB_ROOT_PATH, NLTK_DATA_PATH, JUPYTER_WORK_PATH, WEB_CRAWL_PATH, NEBULA_PATH, CHROMA_PERSISTENT_PATH, LOCAL_LLM_MODEL_DIR, LOCAL_EM_MODEL_DIR]:
if not os.path.exists(_path):
os.makedirs(_path, exist_ok=True)
diff --git a/configs/model_config.py.example b/configs/model_config.py.example
index d4a0325..9cdf892 100644
--- a/configs/model_config.py.example
+++ b/configs/model_config.py.example
@@ -4,6 +4,7 @@ import logging
import torch
import openai
import base64
+import json
from .utils import is_running_in_docker
from .default_config import *
# 日志格式
@@ -29,26 +30,35 @@ try:
client.visit_domain = os.environ.get("visit_domain")
client.visit_biz = os.environ.get("visit_biz")
client.visit_biz_line = os.environ.get("visit_biz_line")
-except:
+except Exception as e:
+ OPENAI_API_BASE = "https://api.openai.com/v1"
+ logger.error(e)
pass
+
+try:
+ with open("./local_config.json", "r") as f:
+ update_config = json.load(f)
+except:
+ update_config = {}
+
+
# add your openai key
-OPENAI_API_BASE = "https://api.openai.com/v1"
-os.environ["API_BASE_URL"] = OPENAI_API_BASE
-os.environ["OPENAI_API_KEY"] = "sk-xx"
-openai.api_key = "sk-xx"
+os.environ["API_BASE_URL"] = os.environ.get("API_BASE_URL") or update_config.get("API_BASE_URL") or OPENAI_API_BASE
+os.environ["OPENAI_API_KEY"] = os.environ.get("OPENAI_API_KEY") or update_config.get("OPENAI_API_KEY") or "sk-xx"
+openai.api_key = os.environ["OPENAI_API_KEY"]
# os.environ["OPENAI_PROXY"] = "socks5h://127.0.0.1:13659"
-os.environ["DUCKDUCKGO_PROXY"] = os.environ.get("DUCKDUCKGO_PROXY") or "socks5://127.0.0.1:13659"
+os.environ["DUCKDUCKGO_PROXY"] = os.environ.get("DUCKDUCKGO_PROXY") or update_config.get("DUCKDUCKGO_PROXY") or "socks5h://127.0.0.1:13659"
# ignore if you dont's use baidu_ocr_api
os.environ["BAIDU_OCR_API_KEY"] = "xx"
os.environ["BAIDU_OCR_SECRET_KEY"] = "xx"
os.environ["log_verbose"] = "2"
# LLM 名称
-EMBEDDING_ENGINE = 'model' # openai or model
-EMBEDDING_MODEL = "text2vec-base"
-LLM_MODEL = "gpt-3.5-turbo"
-LLM_MODELs = ["gpt-3.5-turbo"]
+EMBEDDING_ENGINE = os.environ.get("EMBEDDING_ENGINE") or update_config.get("EMBEDDING_ENGINE") or 'model' # openai or model
+EMBEDDING_MODEL = os.environ.get("EMBEDDING_MODEL") or update_config.get("EMBEDDING_MODEL") or "text2vec-base"
+LLM_MODEL = os.environ.get("LLM_MODEL") or "gpt-3.5-turbo"
+LLM_MODELs = [LLM_MODEL]
USE_FASTCHAT = "gpt" not in LLM_MODEL # 判断是否进行fastchat
# LLM 运行设备
@@ -57,10 +67,12 @@ LLM_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mp
# 在以下字典中修改属性值，以指定本地embedding模型存储位置
# 如将 "text2vec": "GanymedeNil/text2vec-large-chinese" 修改为 "text2vec": "User/Downloads/text2vec-large-chinese"
# 此处请写绝对路径
-embedding_model_dict = {
+embedding_model_dict = json.loads(os.environ.get("embedding_model_dict")) if os.environ.get("embedding_model_dict") else {}
+embedding_model_dict = embedding_model_dict or update_config.get("EMBEDDING_MODEL")
+embedding_model_dict = embedding_model_dict or {
"ernie-tiny": "nghuyong/ernie-3.0-nano-zh",
"ernie-base": "nghuyong/ernie-3.0-base-zh",
- "text2vec-base": "shibing624/text2vec-base-chinese",
+ "text2vec-base": "text2vec-base-chinese",
"text2vec": "GanymedeNil/text2vec-large-chinese",
"text2vec-paraphrase": "shibing624/text2vec-base-chinese-paraphrase",
"text2vec-sentence": "shibing624/text2vec-base-chinese-sentence",
@@ -74,31 +86,35 @@ embedding_model_dict = {
}
-LOCAL_MODEL_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "embedding_models")
-embedding_model_dict = {k: f"/home/user/chatbot/embedding_models/{v}" if is_running_in_docker() else f"{LOCAL_MODEL_DIR}/{v}" for k, v in embedding_model_dict.items()}
+# LOCAL_MODEL_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "embedding_models")
+# embedding_model_dict = {k: f"/home/user/chatbot/embedding_models/{v}" if is_running_in_docker() else f"{LOCAL_MODEL_DIR}/{v}" for k, v in embedding_model_dict.items()}
# Embedding 模型运行设备
EMBEDDING_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
-ONLINE_LLM_MODEL = {
+ONLINE_LLM_MODEL = json.loads(os.environ.get("ONLINE_LLM_MODEL")) if os.environ.get("ONLINE_LLM_MODEL") else {}
+ONLINE_LLM_MODEL = ONLINE_LLM_MODEL or update_config.get("ONLINE_LLM_MODEL")
+ONLINE_LLM_MODEL = ONLINE_LLM_MODEL or {
# 线上模型。请在server_config中为每个在线API设置不同的端口
"openai-api": {
"model_name": "gpt-3.5-turbo",
- "api_base_url": "https://api.openai.com/v1",
+ "api_base_url": OPENAI_API_BASE, # "https://api.openai.com/v1",
"api_key": "",
"openai_proxy": "",
},
"example": {
- "version": "gpt-3.5", # 采用openai接口做示例
- "api_base_url": "https://api.openai.com/v1",
+ "version": "gpt-3.5-turbo", # 采用openai接口做示例
+ "api_base_url": OPENAI_API_BASE, # "https://api.openai.com/v1",
"api_key": "",
"provider": "ExampleWorker",
},
}
# 建议使用chat模型，不要使用base，无法获取正确输出
-llm_model_dict = {
+llm_model_dict = json.loads(os.environ.get("llm_model_dict")) if os.environ.get("llm_model_dict") else {}
+llm_model_dict = llm_model_dict or update_config.get("llm_model_dict")
+llm_model_dict = llm_model_dict or {
"chatglm-6b": {
"local_model_path": "THUDM/chatglm-6b",
"api_base_url": "http://localhost:8888/v1", # "name"修改为fastchat服务中的"api_base_url"
@@ -147,7 +163,9 @@ llm_model_dict = {
}
# 建议使用chat模型，不要使用base，无法获取正确输出
-VLLM_MODEL_DICT = {
+VLLM_MODEL_DICT = json.loads(os.environ.get("VLLM_MODEL_DICT")) if os.environ.get("VLLM_MODEL_DICT") else {}
+VLLM_MODEL_DICT = VLLM_MODEL_DICT or update_config.get("VLLM_MODEL_DICT")
+VLLM_MODEL_DICT = VLLM_MODEL_DICT or {
'chatglm2-6b': "THUDM/chatglm-6b",
}
# 以下模型经过测试可接入，配置仿照上述即可
@@ -157,21 +175,21 @@ VLLM_MODEL_DICT = {
# 'chatglm3-6b-base', 'Qwen-72B-Chat-Int4'
-LOCAL_LLM_MODEL_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "llm_models")
-# 模型路径重置
-llm_model_dict_c = {}
-for k, v in llm_model_dict.items():
- v_c = {}
- for kk, vv in v.items():
- if k=="local_model_path":
- v_c[kk] = f"/home/user/chatbot/llm_models/{vv}" if is_running_in_docker() else f"{LOCAL_LLM_MODEL_DIR}/{vv}"
- else:
- v_c[kk] = vv
- llm_model_dict_c[k] = v_c
+# LOCAL_LLM_MODEL_DIR = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "llm_models")
+# # 模型路径重置
+# llm_model_dict_c = {}
+# for k, v in llm_model_dict.items():
+# v_c = {}
+# for kk, vv in v.items():
+# if k=="local_model_path":
+# v_c[kk] = f"/home/user/chatbot/llm_models/{vv}" if is_running_in_docker() else f"{LOCAL_LLM_MODEL_DIR}/{vv}"
+# else:
+# v_c[kk] = vv
+# llm_model_dict_c[k] = v_c
-llm_model_dict = llm_model_dict_c
-#
-VLLM_MODEL_DICT_c = {}
-for k, v in VLLM_MODEL_DICT.items():
- VLLM_MODEL_DICT_c[k] = f"/home/user/chatbot/llm_models/{v}" if is_running_in_docker() else f"{LOCAL_LLM_MODEL_DIR}/{v}"
-VLLM_MODEL_DICT = VLLM_MODEL_DICT_c
\ No newline at end of file
+# llm_model_dict = llm_model_dict_c
+# #
+# VLLM_MODEL_DICT_c = {}
+# for k, v in VLLM_MODEL_DICT.items():
+# VLLM_MODEL_DICT_c[k] = f"/home/user/chatbot/llm_models/{v}" if is_running_in_docker() else f"{LOCAL_LLM_MODEL_DIR}/{v}"
+# VLLM_MODEL_DICT = VLLM_MODEL_DICT_c
\ No newline at end of file
diff --git a/configs/server_config.py.example b/configs/server_config.py.example
index c313cf0..f22fa6b 100644
--- a/configs/server_config.py.example
+++ b/configs/server_config.py.example
@@ -1,13 +1,25 @@
from .model_config import LLM_MODEL, LLM_DEVICE
-import os
+import os, json
+
+try:
+ with open("./local_config.json", "r") as f:
+ update_config = json.load(f)
+except:
+ update_config = {}
# API 是否开启跨域，默认为False，如果需要开启，请设置为True
# is open cross domain
OPEN_CROSS_DOMAIN = False
# 是否用容器来启动服务
-DOCKER_SERVICE = True
+try:
+ DOCKER_SERVICE = json.loads(os.environ["DOCKER_SERVICE"]) or update_config.get("DOCKER_SERVICE") or False
+except:
+ DOCKER_SERVICE = True
# 是否采用容器沙箱
-SANDBOX_DO_REMOTE = True
+try:
+ SANDBOX_DO_REMOTE = json.loads(os.environ["SANDBOX_DO_REMOTE"]) or update_config.get("SANDBOX_DO_REMOTE") or False
+except:
+ SANDBOX_DO_REMOTE = True
# 是否采用api服务来进行
NO_REMOTE_API = True
# 各服务器默认绑定host
@@ -61,7 +73,7 @@ NEBULA_GRAPH_SERVER = {
# sandbox api server
SANDBOX_CONTRAINER_NAME = "devopsgpt_sandbox"
SANDBOX_IMAGE_NAME = "devopsgpt:py39"
-SANDBOX_HOST = os.environ.get("SANDBOX_HOST") or DEFAULT_BIND_HOST # "172.25.0.3"
+SANDBOX_HOST = os.environ.get("SANDBOX_HOST") or update_config.get("SANDBOX_HOST") or DEFAULT_BIND_HOST # "172.25.0.3"
SANDBOX_SERVER = {
"host": f"http://{SANDBOX_HOST}",
"port": 5050,
@@ -73,7 +85,10 @@ SANDBOX_SERVER = {
# fastchat model_worker server
# 这些模型必须是在model_config.llm_model_dict中正确配置的。
# 在启动startup.py时，可用通过`--model-worker --model-name xxxx`指定模型，不指定则为LLM_MODEL
-FSCHAT_MODEL_WORKERS = {
+# 建议使用chat模型，不要使用base，无法获取正确输出
+FSCHAT_MODEL_WORKERS = json.loads(os.environ.get("FSCHAT_MODEL_WORKERS")) if os.environ.get("FSCHAT_MODEL_WORKERS") else {}
+FSCHAT_MODEL_WORKERS = FSCHAT_MODEL_WORKERS or update_config.get("FSCHAT_MODEL_WORKERS")
+FSCHAT_MODEL_WORKERS = FSCHAT_MODEL_WORKERS or {
"default": {
"host": DEFAULT_BIND_HOST,
"port": 20002,
@@ -117,7 +132,9 @@ FSCHAT_MODEL_WORKERS = {
'chatglm3-6b-32k': {'host': DEFAULT_BIND_HOST, 'port': 20018},
'chatglm3-6b-base': {'host': DEFAULT_BIND_HOST, 'port': 20019},
'Qwen-72B-Chat-Int4': {'host': DEFAULT_BIND_HOST, 'port': 20020},
- 'gpt-3.5-turbo': {'host': DEFAULT_BIND_HOST, 'port': 20021}
+ 'gpt-3.5-turbo': {'host': DEFAULT_BIND_HOST, 'port': 20021},
+ 'example': {'host': DEFAULT_BIND_HOST, 'port': 20022},
+ 'openai-api': {'host': DEFAULT_BIND_HOST, 'port': 20023}
}
# fastchat multi model worker server
FSCHAT_MULTI_MODEL_WORKERS = {
diff --git a/examples/agent_examples/codeChatPhaseLocal_example.py b/examples/agent_examples/codeChatPhaseLocal_example.py
index ff5ee24..172eebc 100644
--- a/examples/agent_examples/codeChatPhaseLocal_example.py
+++ b/examples/agent_examples/codeChatPhaseLocal_example.py
@@ -41,24 +41,16 @@ embed_config = EmbedConfig(
# delete codebase
-codebase_name = 'client_local'
+codebase_name = 'client_nebula'
code_path = '/Users/bingxu/Desktop/工作/大模型/chatbot/test_code_repo/client'
code_path = "D://chromeDownloads/devopschat-bot/client_v2/client"
use_nh = True
-# cbh = CodeBaseHandler(codebase_name, code_path, crawl_type='dir', use_nh=use_nh, local_graph_path=CB_ROOT_PATH,
-# llm_config=llm_config, embed_config=embed_config)
+do_interpret = False
cbh = CodeBaseHandler(codebase_name, code_path, crawl_type='dir', use_nh=use_nh, local_graph_path=CB_ROOT_PATH,
llm_config=llm_config, embed_config=embed_config)
cbh.delete_codebase(codebase_name=codebase_name)
-
# initialize codebase
-codebase_name = 'client_local'
-code_path = '/Users/bingxu/Desktop/工作/大模型/chatbot/test_code_repo/client'
-code_path = "D://chromeDownloads/devopschat-bot/client_v2/client"
-code_path = "/home/user/client"
-use_nh = True
-do_interpret = True
cbh = CodeBaseHandler(codebase_name, code_path, crawl_type='dir', use_nh=use_nh, local_graph_path=CB_ROOT_PATH,
llm_config=llm_config, embed_config=embed_config)
cbh.import_code(do_interpret=do_interpret)
@@ -78,25 +70,25 @@ phase = BasePhase(
## 需要启动容器中的nebula，采用use_nh=True来构建代码库，是可以通过cypher来查询
# round-1
-# query_content = "代码一共有多少类"
-# query = Message(
-# role_name="human", role_type="user",
-# role_content=query_content, input_query=query_content, origin_query=query_content,
-# code_engine_name="client_1", score_threshold=1.0, top_k=3, cb_search_type="cypher"
-# )
-#
-# output_message1, _ = phase.step(query)
-# print(output_message1)
+query_content = "代码一共有多少类"
+query = Message(
+ role_name="human", role_type="user",
+ role_content=query_content, input_query=query_content, origin_query=query_content,
+ code_engine_name="client_1", score_threshold=1.0, top_k=3, cb_search_type="cypher"
+ )
+
+output_message1, _ = phase.step(query)
+print(output_message1)
# round-2
-# query_content = "代码库里有哪些函数，返回5个就行"
-# query = Message(
-# role_name="human", role_type="user",
-# role_content=query_content, input_query=query_content, origin_query=query_content,
-# code_engine_name="client_1", score_threshold=1.0, top_k=3, cb_search_type="cypher"
-# )
-# output_message2, _ = phase.step(query)
-# print(output_message2)
+query_content = "代码库里有哪些函数，返回5个就行"
+query = Message(
+ role_name="human", role_type="user",
+ role_content=query_content, input_query=query_content, origin_query=query_content,
+ code_engine_name="client_1", score_threshold=1.0, top_k=3, cb_search_type="cypher"
+ )
+output_message2, _ = phase.step(query)
+print(output_message2)
# round-3
diff --git a/examples/agent_examples/searchChatPhase_example.py b/examples/agent_examples/searchChatPhase_example.py
index cecafb7..4049694 100644
--- a/examples/agent_examples/searchChatPhase_example.py
+++ b/examples/agent_examples/searchChatPhase_example.py
@@ -7,7 +7,6 @@ sys.path.append(src_dir)
from configs.model_config import KB_ROOT_PATH, JUPYTER_WORK_PATH
from configs.server_config import SANDBOX_SERVER
-from coagent.tools import toLangchainTools, TOOL_DICT, TOOL_SETS
from coagent.llm_models.llm_config import EmbedConfig, LLMConfig
from coagent.connector.phase import BasePhase
diff --git a/examples/model_workers/__init__.py b/examples/model_workers/__init__.py
index b0e5941..65d2bb6 100644
--- a/examples/model_workers/__init__.py
+++ b/examples/model_workers/__init__.py
@@ -16,3 +16,12 @@ from .baichuan import BaiChuanWorker
from .azure import AzureWorker
from .tiangong import TianGongWorker
from .openai import ExampleWorker
+
+
+IMPORT_MODEL_WORKERS = [
+ ChatGLMWorker, MiniMaxWorker, XingHuoWorker, QianFanWorker, FangZhouWorker,
+ QwenWorker, BaiChuanWorker, AzureWorker, TianGongWorker, ExampleWorker
+]
+
+MODEL_WORKER_SETS = [tool.__name__ for tool in IMPORT_MODEL_WORKERS]
+
diff --git a/examples/model_workers/base.py b/examples/model_workers/base.py
index 88bc51f..9d03149 100644
--- a/examples/model_workers/base.py
+++ b/examples/model_workers/base.py
@@ -1,6 +1,5 @@
from fastchat.conversation import Conversation
-from configs.model_config import LOG_PATH
-# from coagent.base_configs.env_config import LOG_PATH
+from configs.default_config import LOG_PATH
import fastchat.constants
fastchat.constants.LOGDIR = LOG_PATH
from fastchat.serve.base_model_worker import BaseModelWorker
diff --git a/examples/start.py b/examples/start.py
index 2275cfb..b0e16d6 100644
--- a/examples/start.py
+++ b/examples/start.py
@@ -1,4 +1,4 @@
-import docker, sys, os, time, requests, psutil
+import docker, sys, os, time, requests, psutil, json
import subprocess
from docker.types import Mount, DeviceRequest
from loguru import logger
@@ -25,9 +25,6 @@ def check_process(content: str, lang: str = None, do_stop=False):
'''process-not-exist is true, process-exist is false'''
for process in psutil.process_iter(["pid", "name", "cmdline"]):
# check process name contains "jupyter" and port=xx
-
- # if f"port={SANDBOX_SERVER['port']}" in str(process.info["cmdline"]).lower() and \
- # "jupyter" in process.info['name'].lower():
if content in str(process.info["cmdline"]).lower():
logger.info(f"content, {process.info}")
# 关闭进程
@@ -106,7 +103,7 @@ def start_sandbox_service(network_name ='my_network'):
)
mounts = [mount]
# 沙盒的启动与服务的启动是独立的
- if SANDBOX_SERVER["do_remote"]:
+ if SANDBOX_DO_REMOTE:
client = docker.from_env()
networks = client.networks.list()
if any([network_name==i.attrs["Name"] for i in networks]):
@@ -159,18 +156,6 @@ def start_api_service(sandbox_host=DEFAULT_BIND_HOST):
target='/home/user/chatbot/',
read_only=False # 如果需要只读访问，将此选项设置为True
)
- # mount_database = Mount(
- # type='bind',
- # source=os.path.join(src_dir, "knowledge_base"),
- # target='/home/user/knowledge_base/',
- # read_only=False # 如果需要只读访问，将此选项设置为True
- # )
- # mount_code_database = Mount(
- # type='bind',
- # source=os.path.join(src_dir, "code_base"),
- # target='/home/user/code_base/',
- # read_only=False # 如果需要只读访问，将此选项设置为True
- # )
ports={
f"{API_SERVER['docker_port']}/tcp": f"{API_SERVER['port']}/tcp",
f"{WEBUI_SERVER['docker_port']}/tcp": f"{WEBUI_SERVER['port']}/tcp",
@@ -208,6 +193,8 @@ def start_api_service(sandbox_host=DEFAULT_BIND_HOST):
if check_docker(client, CONTRAINER_NAME, do_stop=True):
container = start_docker(client, script_shs, ports, IMAGE_NAME, CONTRAINER_NAME, mounts, network=network_name)
+ logger.info("You can open http://localhost:8501 to use chatbot!")
+
else:
logger.info("start local service")
# 关闭之前启动的docker 服务
@@ -234,12 +221,17 @@ def start_api_service(sandbox_host=DEFAULT_BIND_HOST):
subprocess.Popen(webui_sh, shell=True)
+ logger.info("You can please open http://localhost:8501 to use chatbot!")
-if __name__ == "__main__":
+def start_main():
+ global SANDBOX_DO_REMOTE, DOCKER_SERVICE
+ SANDBOX_DO_REMOTE = SANDBOX_DO_REMOTE if os.environ.get("SANDBOX_DO_REMOTE") is None else json.loads(os.environ.get("SANDBOX_DO_REMOTE"))
+ DOCKER_SERVICE = DOCKER_SERVICE if os.environ.get("DOCKER_SERVICE") is None else json.loads(os.environ.get("DOCKER_SERVICE"))
+
start_sandbox_service()
sandbox_host = DEFAULT_BIND_HOST
- if SANDBOX_SERVER["do_remote"]:
+ if SANDBOX_DO_REMOTE:
client = docker.from_env()
containers = client.containers.list(all=True)
@@ -252,3 +244,5 @@ if __name__ == "__main__":
start_api_service(sandbox_host)
+if __name__ == "__main__":
+ start_main()
diff --git a/examples/start.sh b/examples/start.sh
new file mode 100644
index 0000000..ac52ee3
--- /dev/null
+++ b/examples/start.sh
@@ -0,0 +1,7 @@
+#!/bin/bash
+
+
+cp ../configs/model_config.py.example ../configs/model_config.py
+cp ../configs/server_config.py.example ../configs/server_config.py
+
+streamlit run webui_config.py --server.port 8510
diff --git a/examples/stop.py b/examples/stop.py
index 0c8f3ea..2ed3dac 100644
--- a/examples/stop.py
+++ b/examples/stop.py
@@ -17,14 +17,20 @@ try:
except:
client = None
-#
-check_docker(client, SANDBOX_CONTRAINER_NAME, do_stop=True, )
-check_process(f"port={SANDBOX_SERVER['port']}", do_stop=True)
-check_process(f"port=5050", do_stop=True)
-#
-check_docker(client, CONTRAINER_NAME, do_stop=True, )
-check_process("api.py", do_stop=True)
-check_process("sdfile_api.py", do_stop=True)
-check_process("llm_api.py", do_stop=True)
-check_process("webui.py", do_stop=True)
+def stop_main():
+ #
+ check_docker(client, SANDBOX_CONTRAINER_NAME, do_stop=True, )
+ check_process(f"port={SANDBOX_SERVER['port']}", do_stop=True)
+ check_process(f"port=5050", do_stop=True)
+
+ #
+ check_docker(client, CONTRAINER_NAME, do_stop=True, )
+ check_process("api.py", do_stop=True)
+ check_process("sdfile_api.py", do_stop=True)
+ check_process("llm_api.py", do_stop=True)
+ check_process("webui.py", do_stop=True)
+
+
+if __name__ == "__main__":
+ stop_main()
\ No newline at end of file
diff --git a/examples/webui/document.py b/examples/webui/document.py
index 104cb36..ad5b2a9 100644
--- a/examples/webui/document.py
+++ b/examples/webui/document.py
@@ -357,7 +357,7 @@ def knowledge_page(
empty.progress(0.0, "")
for d in api.recreate_vector_store(
kb, vs_type=default_vs_type, embed_model=embedding_model, embedding_device=EMBEDDING_DEVICE,
- embed_model_path=embedding_model_dict[EMBEDDING_MODEL], embed_engine=EMBEDDING_ENGINE,
+ embed_model_path=embedding_model_dict[embedding_model], embed_engine=EMBEDDING_ENGINE,
api_key=llm_model_dict[LLM_MODEL]["api_key"],
api_base_url=llm_model_dict[LLM_MODEL]["api_base_url"],
):
diff --git a/examples/webui_config.py b/examples/webui_config.py
new file mode 100644
index 0000000..08af1d5
--- /dev/null
+++ b/examples/webui_config.py
@@ -0,0 +1,208 @@
+import streamlit as st
+import docker
+import torch, os, sys, json
+from loguru import logger
+
+src_dir = os.path.join(
+ os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+)
+sys.path.append(src_dir)
+from configs.default_config import *
+
+import platform
+system_name = platform.system()
+
+
+VERSION = "v0.1.0"
+
+MODEL_WORKER_SETS = [
+ "ChatGLMWorker", "MiniMaxWorker", "XingHuoWorker", "QianFanWorker", "FangZhouWorker",
+ "QwenWorker", "BaiChuanWorker", "AzureWorker", "TianGongWorker", "ExampleWorker"
+]
+
+openai_models = ["gpt-3.5-turbo", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-4"]
+embedding_models = ["openai"]
+
+
+st.write("启动配置页面！")
+
+st.write("如果你要使用语言模型，请将LLM放到 ~/Codefuse-chatbot/llm_models")
+
+st.write("如果你要使用向量模型，请将向量模型放到 ~/Codefuse-chatbot/embedding_models")
+
+with st.container():
+
+ col1, col2 = st.columns(2)
+ with col1.container():
+ llm_model_name = st.selectbox('LLM Model Name', openai_models + [i for i in os.listdir(LOCAL_LLM_MODEL_DIR) if os.path.isdir(os.path.join(LOCAL_LLM_MODEL_DIR, i))])
+
+ llm_apikey = st.text_input('填写 LLM API KEY', 'EMPTY')
+ llm_apiurl = st.text_input('填写 LLM API URL', 'http://localhost:8888/v1')
+
+ llm_engine = st.selectbox('选择哪个llm引擎', ["online", "fastchat", "fastchat-vllm"])
+ llm_model_port = st.text_input('LLM Model Port，非fastchat模式可无视', '20006')
+ llm_provider_option = st.selectbox('选择哪个online模型加载器，非online可无视', ["openai"] + MODEL_WORKER_SETS)
+
+ if llm_engine == "online" and llm_provider_option == "openai":
+ try:
+ from zdatafront import OPENAI_API_BASE
+ except:
+ OPENAI_API_BASE = "https://api.openai.com/v1"
+ llm_apiurl = OPENAI_API_BASE
+
+ device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
+
+ FSCHAT_MODEL_WORKERS = {
+ llm_model_name: {
+ 'host': "127.0.0.1", 'port': llm_model_port,
+ "device": device,
+ # todo: 多卡加载需要配置的参数
+ "gpus": None,
+ "numgpus": 1,},
+ }
+
+
+ ONLINE_LLM_MODEL, llm_model_dict, VLLM_MODEL_DICT = {}, {}, {}
+ if llm_engine == "online":
+ ONLINE_LLM_MODEL = {
+ llm_model_name: {
+ "model_name": llm_model_name,
+ "version": llm_model_name,
+ "api_base_url": llm_apiurl, # "https://api.openai.com/v1",
+ "api_key": llm_apikey,
+ "openai_proxy": "",
+ "provider": llm_provider_option
+ },
+ }
+
+ if llm_engine == "fastchat":
+ llm_model_dict = {
+ llm_model_name: {
+ "local_model_path": llm_model_name,
+ "api_base_url": llm_apiurl, # "name"修改为fastchat服务中的"api_base_url"
+ "api_key": llm_apikey
+ }}
+
+
+ if llm_engine == "fastchat-vllm":
+ VLLM_MODEL_DICT = {
+ llm_model_name: {
+ "local_model_path": llm_model_name,
+ "api_base_url": llm_apiurl, # "name"修改为fastchat服务中的"api_base_url"
+ "api_key": llm_apikey
+ }
+ }
+ llm_model_dict = {
+ llm_model_name: {
+ "local_model_path": llm_model_name,
+ "api_base_url": llm_apiurl, # "name"修改为fastchat服务中的"api_base_url"
+ "api_key": llm_apikey
+ }}
+
+
+ with col2.container():
+ em_model_name = st.selectbox('Embedding Model Name', [i for i in os.listdir(LOCAL_EM_MODEL_DIR) if os.path.isdir(os.path.join(LOCAL_EM_MODEL_DIR, i))] + embedding_models)
+ em_engine = st.selectbox('选择哪个embedding引擎', ["model", "openai"])
+ device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
+ embedding_model_dict = {em_model_name: em_model_name}
+ # em_apikey = st.text_input('Embedding API KEY', '')
+ # em_apiurl = st.text_input('Embedding API URL', '')
+
+#
+try:
+ client = docker.from_env()
+ has_docker = True
+except:
+ has_docker = False
+
+if has_docker:
+ with st.container():
+ DOCKER_SERVICE = st.toggle('DOCKER_SERVICE', True)
+ SANDBOX_DO_REMOTE = st.toggle('SANDBOX_DO_REMOTE', True)
+else:
+ DOCKER_SERVICE = False
+ SANDBOX_DO_REMOTE = False
+
+
+with st.container():
+ cols = st.columns(3)
+
+ if cols[0].button(
+ "重启服务，按前配置生效",
+ use_container_width=True,
+ ):
+ from start import start_main
+ from stop import stop_main
+ stop_main()
+ start_main()
+ if cols[1].button(
+ "停止服务",
+ use_container_width=True,
+ ):
+ from stop import stop_main
+ stop_main()
+
+ if cols[2].button(
+ "启动对话服务",
+ use_container_width=True
+ ):
+
+ os.environ["API_BASE_URL"] = llm_apiurl
+ os.environ["OPENAI_API_KEY"] = llm_apikey
+
+ os.environ["EMBEDDING_ENGINE"] = em_engine
+ os.environ["EMBEDDING_MODEL"] = em_model_name
+ os.environ["LLM_MODEL"] = llm_model_name
+
+ embedding_model_dict = {k: f"/home/user/chatbot/embedding_models/{v}" if DOCKER_SERVICE else f"{LOCAL_EM_MODEL_DIR}/{v}" for k, v in embedding_model_dict.items()}
+ os.environ["embedding_model_dict"] = json.dumps(embedding_model_dict)
+
+ os.environ["ONLINE_LLM_MODEL"] = json.dumps(ONLINE_LLM_MODEL)
+
+ # 模型路径重置
+ llm_model_dict_c = {}
+ for k, v in llm_model_dict.items():
+ v_c = {}
+ for kk, vv in v.items():
+ if k=="local_model_path":
+ v_c[kk] = f"/home/user/chatbot/llm_models/{vv}" if DOCKER_SERVICE else f"{LOCAL_LLM_MODEL_DIR}/{vv}"
+ else:
+ v_c[kk] = vv
+ llm_model_dict_c[k] = v_c
+
+ llm_model_dict = llm_model_dict_c
+ os.environ["llm_model_dict"] = json.dumps(llm_model_dict)
+ #
+ VLLM_MODEL_DICT_c = {}
+ for k, v in VLLM_MODEL_DICT.items():
+ VLLM_MODEL_DICT_c[k] = f"/home/user/chatbot/llm_models/{v}" if DOCKER_SERVICE else f"{LOCAL_LLM_MODEL_DIR}/{v}"
+ VLLM_MODEL_DICT = VLLM_MODEL_DICT_c
+ os.environ["VLLM_MODEL_DICT"] = json.dumps(VLLM_MODEL_DICT)
+
+ # server config
+ os.environ["DOCKER_SERVICE"] = json.dumps(DOCKER_SERVICE)
+ os.environ["SANDBOX_DO_REMOTE"] = json.dumps(SANDBOX_DO_REMOTE)
+ os.environ["FSCHAT_MODEL_WORKERS"] = json.dumps(FSCHAT_MODEL_WORKERS)
+
+ update_json = {
+ "API_BASE_URL": llm_apiurl,
+ "OPENAI_API_KEY": llm_apikey,
+ "EMBEDDING_ENGINE": em_engine,
+ "EMBEDDING_MODEL": em_model_name,
+ "LLM_MODEL": llm_model_name,
+ "embedding_model_dict": json.dumps(embedding_model_dict),
+ "llm_model_dict": json.dumps(llm_model_dict),
+ "ONLINE_LLM_MODEL": json.dumps(ONLINE_LLM_MODEL),
+ "VLLM_MODEL_DICT": json.dumps(VLLM_MODEL_DICT),
+ "DOCKER_SERVICE": json.dumps(DOCKER_SERVICE),
+ "SANDBOX_DO_REMOTE": json.dumps(SANDBOX_DO_REMOTE),
+ "FSCHAT_MODEL_WORKERS": json.dumps(FSCHAT_MODEL_WORKERS)
+ }
+
+ with open(os.path.join(src_dir, "configs/local_config.json"), "w") as f:
+ json.dump(update_json, f)
+
+ from start import start_main
+ from stop import stop_main
+ stop_main()
+ start_main()
diff --git a/sources/docs_imgs/webui_config.png b/sources/docs_imgs/webui_config.png
new file mode 100644
index 0000000..711b5f7
Binary files /dev/null and b/sources/docs_imgs/webui_config.png differ
diff --git a/tests/chains_test.py b/tests/chains_test.py
index ffc318d..12b5294 100644
--- a/tests/chains_test.py
+++ b/tests/chains_test.py
@@ -79,7 +79,7 @@ print(src_dir)
# chain的测试
llm_config = LLMConfig(
- model_name="gpt-3.5-turbo", model_device="cpu",api_key=os.environ["OPENAI_API_KEY"],
+ model_name="gpt-3.5-turbo", api_key=os.environ["OPENAI_API_KEY"],
api_base_url=os.environ["API_BASE_URL"], temperature=0.3
)
embed_config = EmbedConfig(
diff --git a/tests/openai_test.py b/tests/openai_test.py
index 4186865..1f2c751 100644
--- a/tests/openai_test.py
+++ b/tests/openai_test.py
@@ -5,7 +5,7 @@ src_dir = os.path.join(
)
sys.path.append(src_dir)
-from configs import llm_model_dict, LLM_MODEL
+from configs.model_config import llm_model_dict, LLM_MODEL
import openai
# os.environ["OPENAI_PROXY"] = "socks5h://127.0.0.1:7890"
# os.environ["OPENAI_PROXY"] = "http://127.0.0.1:7890"
@@ -22,30 +22,32 @@ if __name__ == "__main__":
# chat = ChatOpenAI(temperature=0.1, model_name="gpt-3.5-turbo")
# print(chat.predict("hi!"))
- # print(LLM_MODEL, llm_model_dict[LLM_MODEL]["api_key"], llm_model_dict[LLM_MODEL]["api_base_url"])
- # model = ChatOpenAI(
- # streaming=True,
- # verbose=True,
- # openai_api_key=llm_model_dict[LLM_MODEL]["api_key"],
- # openai_api_base=llm_model_dict[LLM_MODEL]["api_base_url"],
- # model_name=LLM_MODEL
- # )
+ print(LLM_MODEL, llm_model_dict[LLM_MODEL]["api_key"], llm_model_dict[LLM_MODEL]["api_base_url"])
+ from langchain.chat_models import ChatOpenAI
+ model = ChatOpenAI(
+ streaming=True,
+ verbose=True,
+ openai_api_key="dsdadas",
+ openai_api_base=llm_model_dict[LLM_MODEL]["api_base_url"],
+ model_name=LLM_MODEL
+ )
+ print(model.predict("hi!"))
# chat_prompt = ChatPromptTemplate.from_messages([("human", "{input}")])
# chain = LLMChain(prompt=chat_prompt, llm=model)
# content = chain({"input": "hello"})
# print(content)
- import openai
- # openai.api_key = "EMPTY" # Not support yet
- openai.api_base = "http://127.0.0.1:8888/v1"
+ # import openai
+ # # openai.api_key = "EMPTY" # Not support yet
+ # openai.api_base = "http://127.0.0.1:8888/v1"
- model = "example"
+ # model = "example"
- # create a chat completion
- completion = openai.ChatCompletion.create(
- model=model,
- messages=[{"role": "user", "content": "Hello! What is your name? "}],
- max_tokens=100,
- )
- # print the completion
- print(completion.choices[0].message.content)
\ No newline at end of file
+ # # create a chat completion
+ # completion = openai.ChatCompletion.create(
+ # model=model,
+ # messages=[{"role": "user", "content": "Hello! What is your name? "}],
+ # max_tokens=100,
+ # )
+ # # print the completion
+ # print(completion.choices[0].message.content)
\ No newline at end of file
diff --git a/tests/sandbox_test.py b/tests/sandbox_test.py
index 6e12bc9..9095cf5 100644
--- a/tests/sandbox_test.py
+++ b/tests/sandbox_test.py
@@ -86,7 +86,8 @@ pycodebox = PyCodeBox(remote_url="http://localhost:5050",
reuslt = pycodebox.chat("```import os\nos.getcwd()```", do_code_exe=True)
print(reuslt)
-reuslt = pycodebox.chat("print('hello world!')", do_code_exe=False)
+# reuslt = pycodebox.chat("```print('hello world!')```", do_code_exe=True)
+reuslt = pycodebox.chat("print('hello world!')", do_code_exe=True)
print(reuslt)