Create app.py

app.py

@@ -0,0 +1,509 @@
+import streamlit as st
+import anthropic, openai, base64, cv2, glob, json, math, os, pytz, random, re, requests, textract, time, zipfile
+import plotly.graph_objects as go
+import streamlit.components.v1 as components
+from datetime import datetime
+from audio_recorder_streamlit import audio_recorder
+from bs4 import BeautifulSoup
+from collections import defaultdict, deque
+from dotenv import load_dotenv
+from gradio_client import Client
+from huggingface_hub import InferenceClient
+from io import BytesIO
+from PIL import Image
+from PyPDF2 import PdfReader
+from urllib.parse import quote
+from xml.etree import ElementTree as ET
+from openai import OpenAI
+import extra_streamlit_components as stx
+from streamlit.runtime.scriptrunner import get_script_run_ctx
+import asyncio
+import edge_tts
+
+# 🔧 Config & Setup
+st.set_page_config(
+    page_title="🚲BikeAI🏆 Claude/GPT Research",
+    page_icon="🚲🏆",
+    layout="wide",
+    initial_sidebar_state="auto",
+    menu_items={
+        'Get Help': 'https://huggingface.co/awacke1',
+        'Report a bug': 'https://huggingface.co/spaces/awacke1',
+        'About': "🚲BikeAI🏆 Claude/GPT Research AI"
+    }
+)
+load_dotenv()
+
+openai_api_key = os.getenv('OPENAI_API_KEY', "")
+anthropic_key = os.getenv('ANTHROPIC_API_KEY_3', "")
+if 'OPENAI_API_KEY' in st.secrets:
+    openai_api_key = st.secrets['OPENAI_API_KEY']
+if 'ANTHROPIC_API_KEY' in st.secrets:
+    anthropic_key = st.secrets["ANTHROPIC_API_KEY"]
+
+openai.api_key = openai_api_key
+claude_client = anthropic.Anthropic(api_key=anthropic_key)
+openai_client = OpenAI(api_key=openai.api_key, organization=os.getenv('OPENAI_ORG_ID'))
+HF_KEY = os.getenv('HF_KEY')
+API_URL = os.getenv('API_URL')
+
+if 'transcript_history' not in st.session_state:
+    st.session_state['transcript_history'] = []
+if 'chat_history' not in st.session_state:
+    st.session_state['chat_history'] = []
+if 'openai_model' not in st.session_state:
+    st.session_state['openai_model'] = "gpt-4o-2024-05-13"
+if 'messages' not in st.session_state:
+    st.session_state['messages'] = []
+if 'last_voice_input' not in st.session_state:
+    st.session_state['last_voice_input'] = ""
+if 'editing_file' not in st.session_state:
+    st.session_state['editing_file'] = None
+if 'edit_new_name' not in st.session_state:
+    st.session_state['edit_new_name'] = ""
+if 'edit_new_content' not in st.session_state:
+    st.session_state['edit_new_content'] = ""
+if 'viewing_prefix' not in st.session_state:
+    st.session_state['viewing_prefix'] = None
+if 'should_rerun' not in st.session_state:
+    st.session_state['should_rerun'] = False
+if 'old_val' not in st.session_state:
+    st.session_state['old_val'] = None
+
+# 🎨 Minimal Custom CSS
+st.markdown("""
+<style>
+    .main { background: linear-gradient(to right, #1a1a1a, #2d2d2d); color: #fff; }
+    .stMarkdown { font-family: 'Helvetica Neue', sans-serif; }
+    .stButton>button {
+        margin-right: 0.5rem;
+    }
+</style>
+""", unsafe_allow_html=True)
+
+FILE_EMOJIS = {
+    "md": "📝",
+    "mp3": "🎵",
+}
+
+def clean_for_speech(text: str) -> str:
+    text = text.replace("\n", " ")
+    text = text.replace("</s>", " ")
+    text = text.replace("#", "")
+    # Remove links
+    text = re.sub(r"\(https?:\/\/[^\)]+\)", "", text)
+    text = re.sub(r"\s+", " ", text).strip()
+    return text
+
+def generate_filename(content, file_type="md"):
+    prefix = datetime.now().strftime("%y%m_%H%M") + "_"
+    words = re.findall(r"\w+", content)
+    name_text = '_'.join(words[:3]) if words else 'file'
+    filename = f"{prefix}{name_text}.{file_type}"
+    return filename
+
+def create_file(prompt, response, file_type="md"):
+    filename = generate_filename(response.strip() if response.strip() else prompt.strip(), file_type)
+    with open(filename, 'w', encoding='utf-8') as f:
+        f.write(prompt + "\n\n" + response)
+    return filename
+
+def get_download_link(file):
+    with open(file, "rb") as f:
+        b64 = base64.b64encode(f.read()).decode()
+    return f'<a href="data:file/zip;base64,{b64}" download="{os.path.basename(file)}">📂 Download {os.path.basename(file)}</a>'
+
+@st.cache_resource
+def speech_synthesis_html(result):
+    html_code = f"""
+    <html><body>
+    <script>
+    var msg = new SpeechSynthesisUtterance("{result.replace('"', '')}");
+    window.speechSynthesis.speak(msg);
+    </script>
+    </body></html>
+    """
+    components.html(html_code, height=0)
+
+async def edge_tts_generate_audio(text, voice="en-US-AriaNeural", rate=0, pitch=0):
+    text = clean_for_speech(text)
+    if not text.strip():
+        return None
+    rate_str = f"{rate:+d}%"
+    pitch_str = f"{pitch:+d}Hz"
+    communicate = edge_tts.Communicate(text, voice, rate=rate_str, pitch=pitch_str)
+    out_fn = generate_filename(text,"mp3")
+    await communicate.save(out_fn)
+    return out_fn
+
+def speak_with_edge_tts(text, voice="en-US-AriaNeural", rate=0, pitch=0):
+    return asyncio.run(edge_tts_generate_audio(text, voice, rate, pitch))
+
+def play_and_download_audio(file_path):
+    if file_path and os.path.exists(file_path):
+        st.audio(file_path)
+        dl_link = f'<a href="data:audio/mpeg;base64,{base64.b64encode(open(file_path,"rb").read()).decode()}" download="{os.path.basename(file_path)}">Download {os.path.basename(file_path)}"</a>'
+        st.markdown(dl_link, unsafe_allow_html=True)
+
+def process_image(image_path, user_prompt):
+    with open(image_path, "rb") as imgf:
+        image_data = imgf.read()
+    b64img = base64.b64encode(image_data).decode("utf-8")
+    resp = openai_client.chat.completions.create(
+        model=st.session_state["openai_model"],
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": [
+                {"type": "text", "text": user_prompt},
+                {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{b64img}"}}
+            ]}
+        ],
+        temperature=0.0,
+    )
+    return resp.choices[0].message.content
+
+def process_audio(audio_path):
+    with open(audio_path, "rb") as f:
+        transcription = openai_client.audio.transcriptions.create(model="whisper-1", file=f)
+    st.session_state.messages.append({"role": "user", "content": transcription.text})
+    return transcription.text
+
+def process_video(video_path, seconds_per_frame=1):
+    vid = cv2.VideoCapture(video_path)
+    total = int(vid.get(cv2.CAP_PROP_FRAME_COUNT))
+    fps = vid.get(cv2.CAP_PROP_FPS)
+    skip = int(fps*seconds_per_frame)
+    frames_b64 = []
+    for i in range(0, total, skip):
+        vid.set(cv2.CAP_PROP_POS_FRAMES, i)
+        ret, frame = vid.read()
+        if not ret: break
+        _, buf = cv2.imencode(".jpg", frame)
+        frames_b64.append(base64.b64encode(buf).decode("utf-8"))
+    vid.release()
+    return frames_b64
+
+def process_video_with_gpt(video_path, prompt):
+    frames = process_video(video_path)
+    resp = openai_client.chat.completions.create(
+        model=st.session_state["openai_model"],
+        messages=[
+            {"role":"system","content":"Analyze video frames."},
+            {"role":"user","content":[
+                {"type":"text","text":prompt},
+                *[{"type":"image_url","image_url":{"url":f"data:image/jpeg;base64,{fr}"}} for fr in frames]
+            ]}
+        ]
+    )
+    return resp.choices[0].message.content
+
+def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, titles_summary=True):
+    start = time.time()
+    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
+    r = client.predict(q,20,"Semantic Search","mistralai/Mixtral-8x7B-Instruct-v0.1",api_name="/update_with_rag_md")
+    refs = r[0]
+    r2 = client.predict(q,"mistralai/Mixtral-8x7B-Instruct-v0.1",True,api_name="/ask_llm")
+    result = f"### 🔎 {q}\n\n{r2}\n\n{refs}"
+
+    st.markdown(result)
+
+    if vocal_summary:
+        main_text = clean_for_speech(r2)
+        audio_file_main = speak_with_edge_tts(main_text)
+        st.write("### 🎙️ Vocal Summary (Short Answer)")
+        play_and_download_audio(audio_file_main)
+
+    if extended_refs:
+        summaries_text = "Here are the summaries from the references: " + refs.replace('"','')
+        summaries_text = clean_for_speech(summaries_text)
+        audio_file_refs = speak_with_edge_tts(summaries_text)
+        st.write("### 📜 Extended References & Summaries")
+        play_and_download_audio(audio_file_refs)
+
+    if titles_summary:
+        titles = []
+        for line in refs.split('\n'):
+            m = re.search(r"\[([^\]]+)\]", line)
+            if m:
+                titles.append(m.group(1))
+        if titles:
+            titles_text = "Here are the titles of the papers: " + ", ".join(titles)
+            titles_text = clean_for_speech(titles_text)
+            audio_file_titles = speak_with_edge_tts(titles_text)
+            st.write("### 🔖 Paper Titles")
+            play_and_download_audio(audio_file_titles)
+
+    elapsed = time.time()-start
+    st.write(f"**Total Elapsed:** {elapsed:.2f} s")
+    create_file(q, result, "md")
+    return result
+
+def process_with_gpt(text):
+    if not text: return
+    st.session_state.messages.append({"role":"user","content":text})
+    with st.chat_message("user"):
+        st.markdown(text)
+    with st.chat_message("assistant"):
+        c = openai_client.chat.completions.create(
+            model=st.session_state["openai_model"],
+            messages=st.session_state.messages,
+            stream=False
+        )
+        ans = c.choices[0].message.content
+        st.write("GPT-4o: " + ans)
+        create_file(text, ans, "md")
+        st.session_state.messages.append({"role":"assistant","content":ans})
+    return ans
+
+def process_with_claude(text):
+    if not text: return
+    with st.chat_message("user"):
+        st.markdown(text)
+    with st.chat_message("assistant"):
+        r = claude_client.messages.create(
+            model="claude-3-sonnet-20240229",
+            max_tokens=1000,
+            messages=[{"role":"user","content":text}]
+        )
+        ans = r.content[0].text
+        st.write("Claude-3.5: " + ans)
+        create_file(text, ans, "md")
+        st.session_state.chat_history.append({"user":text,"claude":ans})
+    return ans
+
+def create_zip_of_files(md_files, mp3_files):
+    md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
+    all_files = md_files + mp3_files
+    if not all_files:
+        return None
+    stems = [os.path.splitext(os.path.basename(f))[0] for f in all_files]
+    joined = "_".join(stems)
+    if len(joined) > 50:
+        joined = joined[:50] + "_etc"
+    zip_name = f"{joined}.zip"
+    with zipfile.ZipFile(zip_name,'w') as z:
+        for f in all_files:
+            z.write(f)
+    return zip_name
+
+def load_files_for_sidebar():
+    md_files = glob.glob("*.md")
+    mp3_files = glob.glob("*.mp3")
+
+    md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
+
+    all_files = md_files + mp3_files
+
+    groups = defaultdict(list)
+    for f in all_files:
+        fname = os.path.basename(f)
+        prefix = fname[:10]
+        groups[prefix].append(f)
+
+    for prefix in groups:
+        groups[prefix].sort(key=lambda x: os.path.getmtime(x), reverse=True)
+
+    sorted_prefixes = sorted(groups.keys(), key=lambda pre: max(os.path.getmtime(x) for x in groups[pre]), reverse=True)
+    return groups, sorted_prefixes
+
+def extract_keywords_from_md(files):
+    text = ""
+    for f in files:
+        if f.endswith(".md"):
+            c = open(f,'r',encoding='utf-8').read()
+            text += " " + c
+    words = re.findall(r"\w+", text.lower())
+    unique_words = []
+    for w in words:
+        if w not in unique_words:
+            unique_words.append(w)
+        if len(unique_words) == 5:
+            break
+    return unique_words
+
+def display_file_manager_sidebar(groups, sorted_prefixes):
+    st.sidebar.title("🎵 Audio & Document Manager")
+
+    all_md = []
+    all_mp3 = []
+    for prefix in groups:
+        for f in groups[prefix]:
+            if f.endswith(".md"):
+                all_md.append(f)
+            elif f.endswith(".mp3"):
+                all_mp3.append(f)
+
+    top_bar = st.sidebar.columns(3)
+    with top_bar[0]:
+        if st.button("🗑 Del All MD"):
+            for f in all_md:
+                os.remove(f)
+            st.session_state.should_rerun = True
+    with top_bar[1]:
+        if st.button("🗑 Del All MP3"):
+            for f in all_mp3:
+                os.remove(f)
+            st.session_state.should_rerun = True
+    with top_bar[2]:
+        if st.button("⬇️ Zip All"):
+            z = create_zip_of_files(all_md, all_mp3)
+            if z:
+                st.sidebar.markdown(get_download_link(z),unsafe_allow_html=True)
+
+    for prefix in sorted_prefixes:
+        files = groups[prefix]
+        kw = extract_keywords_from_md(files)
+        keywords_str = " ".join(kw) if kw else "No Keywords"
+        with st.sidebar.expander(f"{prefix} Files ({len(files)}) - Keywords: {keywords_str}", expanded=True):
+            c1,c2 = st.columns(2)
+            with c1:
+                if st.button("👀View Group", key="view_group_"+prefix):
+                    st.session_state.viewing_prefix = prefix
+            with c2:
+                if st.button("🗑Del Group", key="del_group_"+prefix):
+                    for f in files:
+                        os.remove(f)
+                    st.success(f"Deleted all files in group {prefix} successfully!")
+                    st.session_state.should_rerun = True
+
+            for f in files:
+                fname = os.path.basename(f)
+                ctime = datetime.fromtimestamp(os.path.getmtime(f)).strftime("%Y-%m-%d %H:%M:%S")
+                st.write(f"**{fname}** - {ctime}")
+
+def run_selected_model(option, user_input):
+    user_input = user_input.strip()
+    if option == "Arxiv":
+        st.subheader("Arxiv Only Results:")
+        perform_ai_lookup(user_input, vocal_summary=True, extended_refs=False, titles_summary=True)
+    elif option == "GPT-4o":
+        process_with_gpt(user_input)
+    elif option == "Claude-3.5":
+        process_with_claude(user_input)
+
+def main():
+    st.sidebar.markdown("### 🚲BikeAI🏆 Multi-Agent Research AI")
+    tab_main = st.radio("Action:",["🎤 Voice Input","📸 Media Gallery","🔍 Search ArXiv","📝 File Editor"],horizontal=True)
+
+    # Removed the old model_choice radio
+    # Instead, we rely on the dropdown in the Process Input section.
+
+    mycomponent = components.declare_component("mycomponent", path="mycomponent")
+    val = mycomponent(my_input_value="Hello")
+
+    # Show input in a text box for editing if detected
+    if val:
+        val_stripped = val.replace('\n', ' ')
+        edited_input = st.text_area("Edit your detected input:", value=val_stripped, height=100)
+        run_option = st.selectbox("Select AI Model:", ["Arxiv", "GPT-4o", "Claude-3.5"])
+        autorun = st.checkbox("AutoRun on input change", value=False)
+
+        input_changed = (val != st.session_state.old_val)
+
+        if autorun and input_changed:
+            # Automatically run the selected model if input changed
+            st.session_state.old_val = val
+            run_selected_model(run_option, edited_input)
+        else:
+            # If not autorun, show a button to run manually
+            if st.button("Process Input"):
+                st.session_state.old_val = val
+                run_selected_model(run_option, edited_input)
+
+
+    if tab_main == "🔍 Search ArXiv":
+        st.subheader("🔍 Search ArXiv")
+        q=st.text_input("Research query:")
+
+        st.markdown("### 🎛️ Audio Generation Options")
+        vocal_summary = st.checkbox("🎙️ Vocal Summary (Short Answer)", value=True)
+        extended_refs = st.checkbox("📜 Extended References & Summaries (Long)", value=False)
+        titles_summary = st.checkbox("🔖 Paper Titles Only", value=True)
+
+        if q and st.button("Run ArXiv Query"):
+            perform_ai_lookup(q, vocal_summary=vocal_summary, extended_refs=extended_refs, titles_summary=titles_summary)
+
+    elif tab_main == "🎤 Voice Input":
+        st.subheader("🎤 Voice Recognition")
+        user_text = st.text_area("Message:", height=100)
+        user_text = user_text.strip().replace('\n', ' ')
+        if st.button("Send 📨"):
+            # Default to GPT-4o here, or you could similarly provide options.
+            process_with_gpt(user_text)
+        st.subheader("📜 Chat History")
+        t1,t2=st.tabs(["Claude History","GPT-4o History"])
+        with t1:
+            for c in st.session_state.chat_history:
+                st.write("**You:**", c["user"])
+                st.write("**Claude:**", c["claude"])
+        with t2:
+            for m in st.session_state.messages:
+                with st.chat_message(m["role"]):
+                    st.markdown(m["content"])
+
+    elif tab_main == "📸 Media Gallery":
+        st.header("🎬 Media Gallery - Images and Videos")
+        tabs = st.tabs(["🖼️ Images", "🎥 Video"])
+        with tabs[0]:
+            imgs = glob.glob("*.png")+glob.glob("*.jpg")
+            if imgs:
+                c = st.slider("Cols",1,5,3)
+                cols = st.columns(c)
+                for i,f in enumerate(imgs):
+                    with cols[i%c]:
+                        st.image(Image.open(f),use_container_width=True)
+                        if st.button(f"👀 Analyze {os.path.basename(f)}", key=f"analyze_{f}"):
+                            a = process_image(f,"Describe this image.")
+                            st.markdown(a)
+            else:
+                st.write("No images found.")
+        with tabs[1]:
+            vids = glob.glob("*.mp4")
+            if vids:
+                for v in vids:
+                    with st.expander(f"🎥 {os.path.basename(v)}"):
+                        st.video(v)
+                        if st.button(f"Analyze {os.path.basename(v)}", key=f"analyze_{v}"):
+                            a = process_video_with_gpt(v,"Describe video.")
+                            st.markdown(a)
+            else:
+                st.write("No videos found.")
+
+    elif tab_main == "📝 File Editor":
+        if getattr(st.session_state,'current_file',None):
+            st.subheader(f"Editing: {st.session_state.current_file}")
+            new_text = st.text_area("Content:", st.session_state.file_content, height=300)
+            if st.button("Save"):
+                with open(st.session_state.current_file,'w',encoding='utf-8') as f:
+                    f.write(new_text)
+                st.success("Updated!")
+                st.session_state.should_rerun = True
+        else:
+            st.write("Select a file from the sidebar to edit.")
+
+    groups, sorted_prefixes = load_files_for_sidebar()
+    display_file_manager_sidebar(groups, sorted_prefixes)
+
+    if st.session_state.viewing_prefix and st.session_state.viewing_prefix in groups:
+        st.write("---")
+        st.write(f"**Viewing Group:** {st.session_state.viewing_prefix}")
+        for f in groups[st.session_state.viewing_prefix]:
+            fname = os.path.basename(f)
+            ext = os.path.splitext(fname)[1].lower().strip('.')
+            st.write(f"### {fname}")
+            if ext == "md":
+                content = open(f,'r',encoding='utf-8').read()
+                st.markdown(content)
+            elif ext == "mp3":
+                st.audio(f)
+            else:
+                st.markdown(get_download_link(f), unsafe_allow_html=True)
+        if st.button("Close Group View"):
+            st.session_state.viewing_prefix = None
+
+    if st.session_state.should_rerun:
+        st.session_state.should_rerun = False
+        st.rerun()
+
+if __name__=="__main__":
+    main()