Master

10_Historical_data_collection.py

@@ -0,0 +1,96 @@
+import streamlit as st
+import anthropic
+import ollama as ol
+import streamlit as st
+from streamlit_mic_recorder import speech_to_text
+import datetime
+import json
+
+def log_interaction(action, data):
+    timestamp = datetime.datetime.now().isoformat()
+    log = {"timestamp": timestamp, "action": action, "data": data}
+    with open("user_interactions_log.json", "a") as logfile:
+        logfile.write(json.dumps(log) + "\n")
+
+def print_txt(text):
+    if any("\u0600" <= c <= "\u06FF" for c in text):  # check if text contains Arabic characters
+        text = f"<p style='direction: rtl; text-align: right;'>{text}</p>"
+    st.markdown(text, unsafe_allow_html=True)
+
+def print_chat_message(message):
+    text = message["content"]
+    if message["role"] == "user":
+        with st.chat_message("user", avatar="🎙️"):
+            print_txt(text)
+    elif message["role"] == "assistant":
+        with st.chat_message("assistant", avatar="🦙"):
+            print_txt(text)
+
+def get_chat_history(key):
+    return st.session_state.chat_history[key]
+
+def init_chat_history(key, system_prompt):
+    if "chat_history" not in st.session_state:
+        st.session_state.chat_history = {}
+    if key not in st.session_state.chat_history:
+        st.session_state.chat_history[key] = [{"role": "system", "content": system_prompt}]
+
+def system_prompt_input(default_prompt):
+    return st.sidebar.text_area("System Prompt", value=default_prompt, height=100)
+
+def llm_selector():
+    ollama_models = [m['name'] for m in ol.list()['models']]
+    with st.sidebar:
+        return st.selectbox("LLM", ollama_models)
+
+
+
+st.title("🕔 Historical data collection")
+uploaded_file = st.file_uploader("Upload an article", type=("txt"))
+
+
+model = llm_selector()
+chat_key = f"对话_chat_history_{model}"  # Unique key for each mode and model
+default_prompt = ("我现在将要给你传送历史数据，你需要整理这个数据然后给我发送清洗后的历史数据。要求格式：json格式。")
+
+system_prompt = system_prompt_input(default_prompt)
+init_chat_history(chat_key, system_prompt)
+chat_history = get_chat_history(chat_key)
+for message in chat_history:
+    print_chat_message(message)
+
+question = st.chat_input()
+
+debug_mode = st.sidebar.checkbox("Debug Mode", value=True)
+log_interaction("User input", {"mode": "对话", "question": question})
+
+if question:
+    prompt = f"""{anthropic.HUMAN_PROMPT} Here's an article:\n\n<article>
+    {question}\n\n</article>\n\n{question}{anthropic.AI_PROMPT}"""
+
+    if question:
+        user_message = {"role": "user", "content": question}
+
+        # if app_mode == "语音识别":
+        print_chat_message(user_message)
+        chat_history.append(user_message)
+        if uploaded_file:
+            article = uploaded_file.read().decode()
+            chat_history.append({"role": "user", "content": article})  # 添加用户上传的文件内容作为对话历史的一部分
+        response = ol.chat(model=model, messages=chat_history)
+        answer = response['message']['content']
+        ai_message = {"role": "assistant", "content": answer}
+        print_chat_message(ai_message)
+        chat_history.append(ai_message)
+        debug_info = {"messages": chat_history, "response": response}
+
+        if debug_mode:
+            st.write("Debug Info: Complete Prompt Interaction")
+            st.json(debug_info)
+
+        # truncate chat history to keep 20 messages max
+        if len(chat_history) > 20:
+            chat_history = chat_history[-20:]
+
+        # update chat history
+        st.session_state.chat_history[chat_key] = chat_history

11_Internet_data_collection.py

@@ -0,0 +1,96 @@
+import streamlit as st
+import anthropic
+import ollama as ol
+import streamlit as st
+from streamlit_mic_recorder import speech_to_text
+import datetime
+import json
+
+def log_interaction(action, data):
+    timestamp = datetime.datetime.now().isoformat()
+    log = {"timestamp": timestamp, "action": action, "data": data}
+    with open("user_interactions_log.json", "a") as logfile:
+        logfile.write(json.dumps(log) + "\n")
+
+def print_txt(text):
+    if any("\u0600" <= c <= "\u06FF" for c in text):  # check if text contains Arabic characters
+        text = f"<p style='direction: rtl; text-align: right;'>{text}</p>"
+    st.markdown(text, unsafe_allow_html=True)
+
+def print_chat_message(message):
+    text = message["content"]
+    if message["role"] == "user":
+        with st.chat_message("user", avatar="🎙️"):
+            print_txt(text)
+    elif message["role"] == "assistant":
+        with st.chat_message("assistant", avatar="🦙"):
+            print_txt(text)
+
+def get_chat_history(key):
+    return st.session_state.chat_history[key]
+
+def init_chat_history(key, system_prompt):
+    if "chat_history" not in st.session_state:
+        st.session_state.chat_history = {}
+    if key not in st.session_state.chat_history:
+        st.session_state.chat_history[key] = [{"role": "system", "content": system_prompt}]
+
+def system_prompt_input(default_prompt):
+    return st.sidebar.text_area("System Prompt", value=default_prompt, height=100)
+
+def llm_selector():
+    ollama_models = [m['name'] for m in ol.list()['models']]
+    with st.sidebar:
+        return st.selectbox("LLM", ollama_models)
+
+
+
+st.title("🖥️ Internet data collection")
+uploaded_file = st.file_uploader("Upload an article", type=("txt"))
+
+
+model = llm_selector()
+chat_key = f"对话_chat_history_{model}"  # Unique key for each mode and model
+default_prompt = ("我现在将要给你传送网情数据,你需要提取这个数据特征之后发给我，要求格式：json格式。")
+
+system_prompt = system_prompt_input(default_prompt)
+init_chat_history(chat_key, system_prompt)
+chat_history = get_chat_history(chat_key)
+for message in chat_history:
+    print_chat_message(message)
+
+question = st.chat_input()
+
+debug_mode = st.sidebar.checkbox("Debug Mode", value=True)
+log_interaction("User input", {"mode": "对话", "question": question})
+
+if question:
+    prompt = f"""{anthropic.HUMAN_PROMPT} Here's an article:\n\n<article>
+    {question}\n\n</article>\n\n{question}{anthropic.AI_PROMPT}"""
+
+    if question:
+        user_message = {"role": "user", "content": question}
+
+        # if app_mode == "语音识别":
+        print_chat_message(user_message)
+        chat_history.append(user_message)
+        if uploaded_file:
+            article = uploaded_file.read().decode()
+            chat_history.append({"role": "user", "content": article})  # 添加用户上传的文件内容作为对话历史的一部分
+        response = ol.chat(model=model, messages=chat_history)
+        answer = response['message']['content']
+        ai_message = {"role": "assistant", "content": answer}
+        print_chat_message(ai_message)
+        chat_history.append(ai_message)
+        debug_info = {"messages": chat_history, "response": response}
+
+        if debug_mode:
+            st.write("Debug Info: Complete Prompt Interaction")
+            st.json(debug_info)
+
+        # truncate chat history to keep 20 messages max
+        if len(chat_history) > 20:
+            chat_history = chat_history[-20:]
+
+        # update chat history
+        st.session_state.chat_history[chat_key] = chat_history

12_Collection_of_superior_task_data.py

@@ -0,0 +1,96 @@
+import streamlit as st
+import anthropic
+import ollama as ol
+import streamlit as st
+from streamlit_mic_recorder import speech_to_text
+import datetime
+import json
+
+def log_interaction(action, data):
+    timestamp = datetime.datetime.now().isoformat()
+    log = {"timestamp": timestamp, "action": action, "data": data}
+    with open("user_interactions_log.json", "a") as logfile:
+        logfile.write(json.dumps(log) + "\n")
+
+def print_txt(text):
+    if any("\u0600" <= c <= "\u06FF" for c in text):  # check if text contains Arabic characters
+        text = f"<p style='direction: rtl; text-align: right;'>{text}</p>"
+    st.markdown(text, unsafe_allow_html=True)
+
+def print_chat_message(message):
+    text = message["content"]
+    if message["role"] == "user":
+        with st.chat_message("user", avatar="🎙️"):
+            print_txt(text)
+    elif message["role"] == "assistant":
+        with st.chat_message("assistant", avatar="🦙"):
+            print_txt(text)
+
+def get_chat_history(key):
+    return st.session_state.chat_history[key]
+
+def init_chat_history(key, system_prompt):
+    if "chat_history" not in st.session_state:
+        st.session_state.chat_history = {}
+    if key not in st.session_state.chat_history:
+        st.session_state.chat_history[key] = [{"role": "system", "content": system_prompt}]
+
+def system_prompt_input(default_prompt):
+    return st.sidebar.text_area("System Prompt", value=default_prompt, height=100)
+
+def llm_selector():
+    ollama_models = [m['name'] for m in ol.list()['models']]
+    with st.sidebar:
+        return st.selectbox("LLM", ollama_models)
+
+
+
+st.title("🪪 Collection of superior task data")
+uploaded_file = st.file_uploader("Upload an article", type=("txt"))
+
+
+model = llm_selector()
+chat_key = f"对话_chat_history_{model}"  # Unique key for each mode and model
+default_prompt = ("我现在将要给你传送上级任务数据，你需要整理这个数据然后给我发送清洗后的任务数据。要求格式：json格式。")
+
+system_prompt = system_prompt_input(default_prompt)
+init_chat_history(chat_key, system_prompt)
+chat_history = get_chat_history(chat_key)
+for message in chat_history:
+    print_chat_message(message)
+
+question = st.chat_input()
+
+debug_mode = st.sidebar.checkbox("Debug Mode", value=True)
+log_interaction("User input", {"mode": "对话", "question": question})
+
+if question:
+    prompt = f"""{anthropic.HUMAN_PROMPT} Here's an article:\n\n<article>
+    {question}\n\n</article>\n\n{question}{anthropic.AI_PROMPT}"""
+
+    if question:
+        user_message = {"role": "user", "content": question}
+
+        # if app_mode == "语音识别":
+        print_chat_message(user_message)
+        chat_history.append(user_message)
+        if uploaded_file:
+            article = uploaded_file.read().decode()
+            chat_history.append({"role": "user", "content": article})  # 添加用户上传的文件内容作为对话历史的一部分
+        response = ol.chat(model=model, messages=chat_history)
+        answer = response['message']['content']
+        ai_message = {"role": "assistant", "content": answer}
+        print_chat_message(ai_message)
+        chat_history.append(ai_message)
+        debug_info = {"messages": chat_history, "response": response}
+
+        if debug_mode:
+            st.write("Debug Info: Complete Prompt Interaction")
+            st.json(debug_info)
+
+        # truncate chat history to keep 20 messages max
+        if len(chat_history) > 20:
+            chat_history = chat_history[-20:]
+
+        # update chat history
+        st.session_state.chat_history[chat_key] = chat_history

1_File_Q&A.py

@@ -0,0 +1,33 @@
+import streamlit as st
+import anthropic
+
+with st.sidebar:
+    anthropic_api_key = st.text_input("Anthropic API Key", key="file_qa_api_key", type="password")
+    "[View the source code](https://github.com/streamlit/llm-examples/blob/main/pages/1_File_Q%26A.py)"
+    "[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/streamlit/llm-examples?quickstart=1)"
+
+st.title("📝 File Q&A with Anthropic")
+uploaded_file = st.file_uploader("Upload an article", type=("txt", "md"))
+question = st.text_input(
+    "Ask something about the article",
+    placeholder="Can you give me a short summary?",
+    disabled=not uploaded_file,
+)
+
+if uploaded_file and question and not anthropic_api_key:
+    st.info("Please add your Anthropic API key to continue.")
+
+if uploaded_file and question and anthropic_api_key:
+    article = uploaded_file.read().decode()
+    prompt = f"""{anthropic.HUMAN_PROMPT} Here's an article:\n\n<article>
+    {article}\n\n</article>\n\n{question}{anthropic.AI_PROMPT}"""
+
+    client = anthropic.Client(api_key=anthropic_api_key)
+    response = client.completions.create(
+        prompt=prompt,
+        stop_sequences=[anthropic.HUMAN_PROMPT],
+        model="claude-v1",  # "claude-2" for Claude 2 model
+        max_tokens_to_sample=100,
+    )
+    st.write("### Answer")
+    st.write(response.completion)

2_Chat_with_search.py

@@ -0,0 +1,48 @@
+import streamlit as st
+
+from langchain.agents import initialize_agent, AgentType
+from langchain.callbacks import StreamlitCallbackHandler
+from langchain.chat_models import ChatOpenAI
+from langchain.tools import DuckDuckGoSearchRun
+
+with st.sidebar:
+    openai_api_key = st.text_input(
+        "OpenAI API Key", key="langchain_search_api_key_openai", type="password"
+    )
+    "[Get an OpenAI API key](https://platform.openai.com/account/api-keys)"
+    "[View the source code](https://github.com/streamlit/llm-examples/blob/main/pages/2_Chat_with_search.py)"
+    "[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/streamlit/llm-examples?quickstart=1)"
+
+st.title("🔎 LangChain - Chat with search")
+
+"""
+In this example, we're using `StreamlitCallbackHandler` to display the thoughts and actions of an agent in an interactive Streamlit app.
+Try more LangChain 🤝 Streamlit Agent examples at [github.com/langchain-ai/streamlit-agent](https://github.com/langchain-ai/streamlit-agent).
+"""
+
+if "messages" not in st.session_state:
+    st.session_state["messages"] = [
+        {"role": "assistant", "content": "Hi, I'm a chatbot who can search the web. How can I help you?"}
+    ]
+
+for msg in st.session_state.messages:
+    st.chat_message(msg["role"]).write(msg["content"])
+
+if prompt := st.chat_input(placeholder="Who won the Women's U.S. Open in 2018?"):
+    st.session_state.messages.append({"role": "user", "content": prompt})
+    st.chat_message("user").write(prompt)
+
+    if not openai_api_key:
+        st.info("Please add your OpenAI API key to continue.")
+        st.stop()
+
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo", openai_api_key=openai_api_key, streaming=True)
+    search = DuckDuckGoSearchRun(name="Search")
+    search_agent = initialize_agent(
+        [search], llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, handle_parsing_errors=True
+    )
+    with st.chat_message("assistant"):
+        st_cb = StreamlitCallbackHandler(st.container(), expand_new_thoughts=False)
+        response = search_agent.run(st.session_state.messages, callbacks=[st_cb])
+        st.session_state.messages.append({"role": "assistant", "content": response})
+        st.write(response)

3_Langchain_Quickstart.py

@@ -0,0 +1,22 @@
+import streamlit as st
+from langchain.llms import OpenAI
+
+st.title("🦜🔗 Langchain Quickstart App")
+
+with st.sidebar:
+    openai_api_key = st.text_input("OpenAI API Key", type="password")
+    "[Get an OpenAI API key](https://platform.openai.com/account/api-keys)"
+
+
+def generate_response(input_text):
+    llm = OpenAI(temperature=0.7, openai_api_key=openai_api_key)
+    st.info(llm(input_text))
+
+
+with st.form("my_form"):
+    text = st.text_area("Enter text:", "What are 3 key advice for learning how to code?")
+    submitted = st.form_submit_button("Submit")
+    if not openai_api_key:
+        st.info("Please add your OpenAI API key to continue.")
+    elif submitted:
+        generate_response(text)