Merge pull request #2783 from chatchat-space/dev

解决部分依赖问题

configs/model_config.py.example

@@ -224,6 +224,7 @@ MODEL_PATH = {
         "dolly-v2-12b": "databricks/dolly-v2-12b",
         "stablelm-tuned-alpha-7b": "stabilityai/stablelm-tuned-alpha-7b",
     },
+
     "reranker": {
         "bge-reranker-large": "BAAI/bge-reranker-large",
         "bge-reranker-base": "BAAI/bge-reranker-base",

configs/server_config.py.example

@@ -40,8 +40,6 @@ FSCHAT_MODEL_WORKERS = {
         "device": LLM_DEVICE,
         # False,'vllm',使用的推理加速框架,使用vllm如果出现HuggingFace通信问题，参见doc/FAQ
         # vllm对一些模型支持还不成熟，暂时默认关闭
-        # fschat=0.2.33的代码有bug, 如需使用，源码修改fastchat.server.vllm_worker，
-        # 将103行中sampling_params = SamplingParams的参数stop=list(stop)修改为stop= [i for i in stop if i!=""]
         "infer_turbo": False,
 
         # model_worker多卡加载需要配置的参数

knowledge_base/samples/content/wiki

@@ -1 +1 @@
-Subproject commit 2f24adb218f23eab00d7fcd7ccf5072f2f35cb3c
+Subproject commit 28f664aa08f8191a70339c9ecbe7a89b35a1032a

requirements.txt

@@ -1,61 +1,66 @@
-torch~=2.1.2
-torchvision~=0.16.2
-torchaudio~=2.1.2
-xformers~=0.0.23.post1
-transformers~=4.36.2
-sentence_transformers~=2.2.2
+torch==2.1.2
+torchvision==0.16.2
+torchaudio==2.1.2
+xformers==0.0.23.post1
+transformers==4.36.2
+sentence_transformers==2.2.2
 langchain==0.0.354
 langchain-experimental==0.0.47
 pydantic==1.10.13
-fschat~=0.2.35
-openai~=1.9.0
-fastapi~=0.109.0
-sse_starlette~=1.8.2
-nltk~=3.8.1
-uvicorn~=0.24.0.post1
-starlette~=0.32.0
-unstructured[all-docs]~=0.12.0
-python-magic-bin; sys_platform ~= 'win32'
-SQLAlchemy~=2.0.25
-faiss-cpu~=1.7.4
-accelerate~=0.24.1
-spacy~=3.7.2
-PyMuPDF~=1.23.16
-rapidocr_onnxruntime~=1.3.8
-requests~=2.31.0
-pathlib~=1.0.1
-pytest~=7.4.3
-numexpr~=2.8.6
-strsimpy~=0.2.1
-markdownify~=0.11.6
-tiktoken~=0.5.2
-tqdm~=4.66.1
-websockets~=12.0
-numpy~=1.24.4
-pandas~=2.0.3
-einops~=0.7.0
-transformers_stream_generator~=0.0.4
-vllm~=0.2.7; sys_platform ~= "linux"
-jq~=1.6.0
-beautifulsoup4~=4.12.2
-pysrt~=1.1.2
-dashscope~=1.13.6 # qwen
-# volcengine~=1.0.119 # fangzhou
+fschat==0.2.35
+openai==1.9.0
+fastapi==0.109.0
+sse_starlette==1.8.2
+nltk==3.8.1
+uvicorn==0.24.0.post1
+starlette==0.35.0
+unstructured[all-docs] # ==0.11.8
+python-magic-bin; sys_platform == 'win32'
+SQLAlchemy==2.0.25
+faiss-cpu==1.7.4
+accelerate==0.24.1
+spacy==3.7.2
+PyMuPDF==1.23.16
+rapidocr_onnxruntime==1.3.8
+requests==2.31.0
+pathlib==1.0.1
+pytest==7.4.3
+numexpr==2.8.6
+strsimpy==0.2.1
+markdownify==0.11.6
+tiktoken==0.5.2
+tqdm==4.66.1
+websockets==12.0
+numpy==1.24.4
+pandas==2.0.3
+einops==0.7.0
+transformers_stream_generator==0.0.4
+vllm==0.2.7; sys_platform == "linux"
+llama-index==0.9.35
+
+#jq==1.6.0
+# beautifulsoup4==4.12.2
+# pysrt==1.1.2
+# dashscope==1.13.6 # qwen
+# volcengine==1.0.119 # fangzhou
 # uncomment libs if you want to use corresponding vector store
-# pymilvus~=2.3.4
-# psycopg2~=2.9.9
-# pgvector~=0.2.4
-# flash-attn~=2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat
-#rapidocr_paddle[gpu]~=1.3.0.post5 # gpu accelleration for ocr of pdf and image files
-arxiv~=2.1.0
-youtube-search~=2.1.2
-duckduckgo-search~=3.9.9
-metaphor-python~=0.1.23
-streamlit~=1.30.0
-streamlit-option-menu~=0.3.12
-streamlit-antd-components~=0.3.1
-streamlit-chatbox~=1.1.11
-streamlit-modal~=0.1.0
-streamlit-aggrid~=0.3.4.post3
-httpx~=0.26.0
-watchdog~=3.0.0
+# pymilvus==2.3.4
+# psycopg2==2.9.9
+# pgvector==0.2.4
+#flash-attn==2.4.2 # For Orion-14B-Chat and Qwen-14B-Chat
+#autoawq==0.1.8 # For Int4
+#rapidocr_paddle[gpu]==1.3.11 # gpu accelleration for ocr of pdf and image files
+
+arxiv==2.1.0
+youtube-search==2.1.2
+duckduckgo-search==3.9.9
+metaphor-python==0.1.23
+streamlit==1.30.0
+streamlit-option-menu==0.3.12
+streamlit-antd-components==0.3.1
+streamlit-chatbox==1.1.11
+streamlit-modal==0.1.0
+streamlit-aggrid==0.3.4.post3
+httpx==0.26.0
+watchdog==3.0.0
+jwt==1.3.1

requirements_api.txt

@@ -9,11 +9,11 @@ langchain-experimental==0.0.47
 pydantic==1.10.13
 fschat==0.2.35
 openai~=1.9.0
-fastapi~=0.108.0
+fastapi~=0.109.0
 sse_starlette==1.8.2
 nltk>=3.8.1
 uvicorn>=0.24.0.post1
-starlette~=0.32.0
+starlette~=0.35.0
 unstructured[all-docs]==0.11.0
 python-magic-bin; sys_platform == 'win32'
 SQLAlchemy==2.0.19
@@ -37,19 +37,21 @@ einops>=0.7.0
 transformers_stream_generator==0.0.4
 vllm==0.2.7; sys_platform == "linux"
 httpx==0.26.0
-llama-index
-jq==1.6.0
-beautifulsoup4~=4.12.2
-pysrt~=1.1.2
-dashscope==1.13.6
-arxiv~=2.1.0
-youtube-search~=2.1.2
-duckduckgo-search~=3.9.9
-metaphor-python~=0.1.23
+llama-index==0.9.35
+
+# jq==1.6.0
+# beautifulsoup4~=4.12.2
+# pysrt~=1.1.2
+# dashscope==1.13.6
+# arxiv~=2.1.0
+# youtube-search~=2.1.2
+# duckduckgo-search~=3.9.9
+# metaphor-python~=0.1.23
 
 # volcengine>=1.0.119
 # pymilvus>=2.3.4
 # psycopg2==2.9.9
 # pgvector>=0.2.4
-# flash-attn>=2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat
-# rapidocr_paddle[gpu]>=1.3.0.post5
+#flash-attn==2.4.2 # For Orion-14B-Chat and Qwen-14B-Chat
+#autoawq==0.1.8 # For Int4
+#rapidocr_paddle[gpu]==1.3.11 # gpu accelleration for ocr of pdf and image files

requirements_lite.txt

@@ -7,9 +7,9 @@ fastapi~=0.109.0
 sse_starlette~=1.8.2
 nltk~=3.8.1
 uvicorn~=0.24.0.post1
-starlette~=0.32.0
+starlette~=0.35.0
 unstructured[all-docs]~=0.12.0
-python-magic-bin; sys_platform ~= 'win32'
+python-magic-bin; sys_platform == 'win32'
 SQLAlchemy~=2.0.25
 faiss-cpu~=1.7.4
 accelerate~=0.24.1
@@ -19,6 +19,8 @@ rapidocr_onnxruntime~=1.3.8
 requests~=2.31.0
 pathlib~=1.0.1
 pytest~=7.4.3
+llama-index==0.9.35
+
 dashscope==1.13.6
 arxiv~=2.1.0
 youtube-search~=2.1.2
@@ -28,5 +30,4 @@ watchdog~=3.0.0
 # volcengine>=1.0.119
 # pymilvus>=2.3.4
 # psycopg2==2.9.9
-# pgvector>=0.2.4
-# flash-attn>=2.4.3 # For Orion-14B-Chat and Qwen-14B-Chat
+# pgvector>=0.2.4

webui_pages/dialogue/dialogue.py

@@ -6,7 +6,7 @@ from datetime import datetime
 import os
 import re
 import time
-from configs import (TEMPERATURE, HISTORY_LEN, PROMPT_TEMPLATES,
+from configs import (TEMPERATURE, HISTORY_LEN, PROMPT_TEMPLATES, LLM_MODELS,
                      DEFAULT_KNOWLEDGE_BASE, DEFAULT_SEARCH_ENGINE, SUPPORT_AGENT_MODEL)
 from server.knowledge_base.utils import LOADER_DICT
 import uuid
@@ -164,12 +164,12 @@ def dialogue_page(api: ApiRequest, is_lite: bool = False):
         available_models = []
         config_models = api.list_config_models()
         if not is_lite:
-            for k, v in config_models.get("local", {}).items():  # 列出配置了有效本地路径的模型
+            for k, v in config_models.get("local", {}).items():
                 if (v.get("model_path_exists")
                         and k not in running_models):
                     available_models.append(k)
-        for k, v in config_models.get("online", {}).items():  # 列出ONLINE_MODELS中直接访问的模型
-            if not v.get("provider") and k not in running_models:
+        for k, v in config_models.get("online", {}).items():
+            if not v.get("provider") and k not in running_models and k in LLM_MODELS:
                 available_models.append(k)
         llm_models = running_models + available_models
         cur_llm_model = st.session_state.get("cur_llm_model", default_model)

webui_pages/utils.py

@@ -437,9 +437,6 @@ class ApiRequest:
             "prompt_name": prompt_name,
         }
 
-        # print(f"received input message:")
-        # pprint(data)
-
         response = self.post(
             "/chat/file_chat",
             json=data,