dftmsg

app.py

@@ -1,85 +1,52 @@
 import streamlit as st
-from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
+from llama_index.core.settings import Settings
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-from llama_index.legacy.callbacks import CallbackManager
 from llama_index.llms.openai_like import OpenAILike
-from dotenv import load_dotenv
 import os
+from dotenv import load_dotenv
+
+# 加载环境变量
 load_dotenv()
-# Create an instance of CallbackManager
-callback_manager = CallbackManager()
 
-api_base_url =  "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
-model = "internlm2.5-latest"
+# 设置 API 参数
+base_url = "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
 api_key = os.getenv("MY_API_KEY")
+model = "internlm2.5-latest"
 
-# api_base_url =  "https://api.siliconflow.cn/v1"
-# model = "internlm/internlm2_5-7b-chat"
-# api_key = "请填写 API Key"
-
-llm =OpenAILike(model=model, api_base=api_base_url, api_key=api_key, is_chat_model=True,callback_manager=callback_manager)
-
-
-
-st.set_page_config(page_title="llama_index_demo", page_icon="🦜🔗")
-st.title("llama_index_demo")
-
-# 初始化模型
-@st.cache_resource
-def init_models():
-    embed_model = HuggingFaceEmbedding(
-        model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
-    )
-    Settings.embed_model = embed_model
-
-    #用初始化llm
-    Settings.llm = llm
-
-    documents = SimpleDirectoryReader("./data").load_data()
-    index = VectorStoreIndex.from_documents(documents)
-    query_engine = index.as_query_engine()
+# 初始化 LLM
+llm = OpenAILike(model=model, api_base=base_url, api_key=api_key, is_chat_model=True)
 
-    return query_engine
+# 初始化一个 HuggingFaceEmbedding 对象，用于将文本转换为向量表示
+embed_model = HuggingFaceEmbedding(
+    model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+)
 
-# 检查是否需要初始化模型
-if 'query_engine' not in st.session_state:
-    st.session_state['query_engine'] = init_models()
+# 将创建的嵌入模型赋值给全局设置的 embed_model 属性
+Settings.embed_model = embed_model
 
-def greet2(question):
-    response = st.session_state['query_engine'].query(question)
-    return response
+# 将创建的 LLM 赋值给全局设置的 llm 属性
+Settings.llm = llm
 
-      
-# Store LLM generated responses
-if "messages" not in st.session_state.keys():
-    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]    
+# 从指定目录读取所有文档，并加载数据到内存中
+documents = SimpleDirectoryReader("/root/llamaindex_demo/data").load_data()
 
-    # Display or clear chat messages
-for message in st.session_state.messages:
-    with st.chat_message(message["role"]):
-        st.write(message["content"])
+# 创建一个 VectorStoreIndex，并使用之前加载的文档来构建索引
+index = VectorStoreIndex.from_documents(documents)
 
-def clear_chat_history():
-    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]
+# 创建一个查询引擎，这个引擎可以接收查询并返回相关文档的响应
+query_engine = index.as_query_engine()
 
-st.sidebar.button('Clear Chat History', on_click=clear_chat_history)
+# 设置页面标题
+st.title("LlamaIndex Chat")
 
-# Function for generating LLaMA2 response
-def generate_llama_index_response(prompt_input):
-    return greet2(prompt_input)
+# 创建一个文本输入框供用户输入问题
+user_input = st.text_input("请输入你的问题:")
 
-# User-provided prompt
-if prompt := st.chat_input():
-    st.session_state.messages.append({"role": "user", "content": prompt})
-    with st.chat_message("user"):
-        st.write(prompt)
+# 按钮用于提交问题
+if st.button("发送"):
+    # 使用查询引擎获取回复
+    response = query_engine.query(user_input)
 
-# Gegenerate_llama_index_response last message is not from assistant
-if st.session_state.messages[-1]["role"] != "assistant":
-    with st.chat_message("assistant"):
-        with st.spinner("Thinking..."):
-            response = generate_llama_index_response(prompt)
-            placeholder = st.empty()
-            placeholder.markdown(response)
-    message = {"role": "assistant", "content": response}
-    st.session_state.messages.append(message)
+    # 显示回复
+    st.write(f"回复: {response}")

ok_bank_app.py

@@ -0,0 +1,85 @@
+import streamlit as st
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, Settings
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+from llama_index.legacy.callbacks import CallbackManager
+from llama_index.llms.openai_like import OpenAILike
+from dotenv import load_dotenv
+import os
+load_dotenv()
+# Create an instance of CallbackManager
+callback_manager = CallbackManager()
+
+api_base_url =  "https://internlm-chat.intern-ai.org.cn/puyu/api/v1/"
+model = "internlm2.5-latest"
+api_key = os.getenv("MY_API_KEY")
+
+# api_base_url =  "https://api.siliconflow.cn/v1"
+# model = "internlm/internlm2_5-7b-chat"
+# api_key = "请填写 API Key"
+
+llm =OpenAILike(model=model, api_base=api_base_url, api_key=api_key, is_chat_model=True,callback_manager=callback_manager)
+
+
+
+st.set_page_config(page_title="llama_index_demo", page_icon="🦜🔗")
+st.title("llama_index_demo")
+
+# 初始化模型
+@st.cache_resource
+def init_models():
+    embed_model = HuggingFaceEmbedding(
+        model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+    )
+    Settings.embed_model = embed_model
+
+    #用初始化llm
+    Settings.llm = llm
+
+    documents = SimpleDirectoryReader("./data").load_data()
+    index = VectorStoreIndex.from_documents(documents)
+    query_engine = index.as_query_engine()
+
+    return query_engine
+
+# 检查是否需要初始化模型
+if 'query_engine' not in st.session_state:
+    st.session_state['query_engine'] = init_models()
+
+def greet2(question):
+    response = st.session_state['query_engine'].query(question)
+    return response
+
+      
+# Store LLM generated responses
+if "messages" not in st.session_state.keys():
+    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]    
+
+    # Display or clear chat messages
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.write(message["content"])
+
+def clear_chat_history():
+    st.session_state.messages = [{"role": "assistant", "content": "你好，我是你的助手，有什么我可以帮助你的吗？"}]
+
+st.sidebar.button('Clear Chat History', on_click=clear_chat_history)
+
+# Function for generating LLaMA2 response
+def generate_llama_index_response(prompt_input):
+    return greet2(prompt_input)
+
+# User-provided prompt
+if prompt := st.chat_input():
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    with st.chat_message("user"):
+        st.write(prompt)
+
+# Gegenerate_llama_index_response last message is not from assistant
+if st.session_state.messages[-1]["role"] != "assistant":
+    with st.chat_message("assistant"):
+        with st.spinner("Thinking..."):
+            response = generate_llama_index_response(prompt)
+            placeholder = st.empty()
+            placeholder.markdown(response)
+    message = {"role": "assistant", "content": response}
+    st.session_state.messages.append(message)

ok_bank_requirements.txt

@@ -0,0 +1,112 @@
+aiohappyeyeballs==2.4.3
+aiohttp==3.11.8
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.6.2.post1
+async-timeout==5.0.1
+attrs==24.2.0
+beautifulsoup4==4.12.3
+certifi==2024.8.30
+charset-normalizer==3.4.0
+click==8.1.7
+dataclasses-json==0.6.7
+Deprecated==1.2.15
+dirtyjson==1.0.8
+distro==1.9.0
+einops==0.7.0
+exceptiongroup==1.2.2
+filelock==3.16.1
+filetype==1.2.0
+frozenlist==1.5.0
+fsspec==2024.10.0
+greenlet==3.1.1
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.28.0
+huggingface-hub==0.26.3
+idna==3.10
+InstructorEmbedding==1.0.1
+Jinja2==3.1.4
+jiter==0.8.0
+joblib==1.4.2
+llama-cloud==0.1.5
+llama-index==0.11.20
+llama-index-agent-openai==0.3.4
+llama-index-cli==0.3.1
+llama-index-core==0.11.23
+llama-index-embeddings-huggingface==0.3.1
+llama-index-embeddings-instructor==0.2.1
+llama-index-embeddings-openai==0.2.5
+llama-index-indices-managed-llama-cloud==0.6.0
+llama-index-legacy==0.9.48.post4
+llama-index-llms-openai==0.2.16
+llama-index-llms-openai-like==0.2.0
+llama-index-llms-replicate==0.3.0
+llama-index-multi-modal-llms-openai==0.2.3
+llama-index-program-openai==0.2.0
+llama-index-question-gen-openai==0.2.0
+llama-index-readers-file==0.2.2
+llama-index-readers-llama-parse==0.3.0
+llama-parse==0.5.15
+MarkupSafe==3.0.2
+marshmallow==3.23.1
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+nest-asyncio==1.6.0
+networkx==3.4.2
+nltk==3.9.1
+numpy==1.26.4
+# nvidia-cublas-cu12==12.1.3.1
+# nvidia-cuda-cupti-cu12==12.1.105
+# nvidia-cuda-nvrtc-cu12==12.1.105
+# nvidia-cuda-runtime-cu12==12.1.105
+# nvidia-cudnn-cu12==9.1.0.70
+# nvidia-cufft-cu12==11.0.2.54
+# nvidia-curand-cu12==10.3.2.106
+# nvidia-cusolver-cu12==11.4.5.107
+# nvidia-cusparse-cu12==12.1.0.106
+# nvidia-nccl-cu12==2.21.5
+# nvidia-nvjitlink-cu12==12.4.127
+# nvidia-nvtx-cu12==12.1.105
+openai==1.55.3
+packaging==24.2
+pandas==2.2.3
+pillow==11.0.0
+propcache==0.2.0
+protobuf==5.26.1
+pydantic==2.10.2
+pydantic_core==2.27.1
+pypdf==4.3.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2024.2
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+sentence-transformers==2.7.0
+six==1.16.0
+sniffio==1.3.1
+soupsieve==2.6
+SQLAlchemy==2.0.36
+striprtf==0.0.26
+sympy==1.13.1
+tenacity==8.5.0
+threadpoolctl==3.5.0
+tiktoken==0.8.0
+tokenizers==0.20.3
+torch==2.5.0
+torchaudio==2.5.0
+torchvision==0.20.0
+tqdm==4.67.1
+transformers==4.46.3
+triton==3.1.0
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.2
+urllib3==2.2.3
+wrapt==1.17.0
+yarl==1.18.0

requirements.txt

@@ -1,112 +1,8 @@
-aiohappyeyeballs==2.4.3
-aiohttp==3.11.8
-aiosignal==1.3.1
-annotated-types==0.7.0
-anyio==4.6.2.post1
-async-timeout==5.0.1
-attrs==24.2.0
-beautifulsoup4==4.12.3
-certifi==2024.8.30
-charset-normalizer==3.4.0
-click==8.1.7
-dataclasses-json==0.6.7
-Deprecated==1.2.15
-dirtyjson==1.0.8
-distro==1.9.0
-einops==0.7.0
-exceptiongroup==1.2.2
-filelock==3.16.1
-filetype==1.2.0
-frozenlist==1.5.0
-fsspec==2024.10.0
-greenlet==3.1.1
-h11==0.14.0
-httpcore==1.0.7
-httpx==0.28.0
-huggingface-hub==0.26.3
-idna==3.10
-InstructorEmbedding==1.0.1
-Jinja2==3.1.4
-jiter==0.8.0
-joblib==1.4.2
-llama-cloud==0.1.5
-llama-index==0.11.20
-llama-index-agent-openai==0.3.4
-llama-index-cli==0.3.1
-llama-index-core==0.11.23
-llama-index-embeddings-huggingface==0.3.1
-llama-index-embeddings-instructor==0.2.1
-llama-index-embeddings-openai==0.2.5
-llama-index-indices-managed-llama-cloud==0.6.0
-llama-index-legacy==0.9.48.post4
-llama-index-llms-openai==0.2.16
-llama-index-llms-openai-like==0.2.0
-llama-index-llms-replicate==0.3.0
-llama-index-multi-modal-llms-openai==0.2.3
-llama-index-program-openai==0.2.0
-llama-index-question-gen-openai==0.2.0
-llama-index-readers-file==0.2.2
-llama-index-readers-llama-parse==0.3.0
-llama-parse==0.5.15
-MarkupSafe==3.0.2
-marshmallow==3.23.1
-mpmath==1.3.0
-multidict==6.1.0
-mypy-extensions==1.0.0
-nest-asyncio==1.6.0
-networkx==3.4.2
-nltk==3.9.1
-numpy==1.26.4
-# nvidia-cublas-cu12==12.1.3.1
-# nvidia-cuda-cupti-cu12==12.1.105
-# nvidia-cuda-nvrtc-cu12==12.1.105
-# nvidia-cuda-runtime-cu12==12.1.105
-# nvidia-cudnn-cu12==9.1.0.70
-# nvidia-cufft-cu12==11.0.2.54
-# nvidia-curand-cu12==10.3.2.106
-# nvidia-cusolver-cu12==11.4.5.107
-# nvidia-cusparse-cu12==12.1.0.106
-# nvidia-nccl-cu12==2.21.5
-# nvidia-nvjitlink-cu12==12.4.127
-# nvidia-nvtx-cu12==12.1.105
-openai==1.55.3
-packaging==24.2
-pandas==2.2.3
-pillow==11.0.0
-propcache==0.2.0
-protobuf==5.26.1
-pydantic==2.10.2
-pydantic_core==2.27.1
-pypdf==4.3.1
-python-dateutil==2.9.0.post0
-python-dotenv==1.0.1
-pytz==2024.2
-PyYAML==6.0.2
-regex==2024.11.6
-requests==2.32.3
-safetensors==0.4.5
-scikit-learn==1.5.2
-scipy==1.14.1
-sentence-transformers==2.7.0
-six==1.16.0
-sniffio==1.3.1
-soupsieve==2.6
-SQLAlchemy==2.0.36
-striprtf==0.0.26
-sympy==1.13.1
-tenacity==8.5.0
-threadpoolctl==3.5.0
-tiktoken==0.8.0
-tokenizers==0.20.3
-torch==2.5.0
-torchaudio==2.5.0
-torchvision==0.20.0
-tqdm==4.67.1
-transformers==4.46.3
-triton==3.1.0
-typing-inspect==0.9.0
-typing_extensions==4.12.2
-tzdata==2024.2
-urllib3==2.2.3
-wrapt==1.17.0
-yarl==1.18.0
+llama-index
+llama-index-llms-replicate
+llama-index-llms-openai-like
+llama-index-embeddings-huggingface
+llama-index-embeddings-instructor
+llama-index-core
+python-dotenv
+openai