awacke1 commited on
Commit
03becb4
·
verified ·
1 Parent(s): 4635abd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +135 -1
README.md CHANGED
@@ -6,7 +6,7 @@ colorTo: purple
6
  sdk: streamlit
7
  sdk_version: 1.41.1
8
  app_file: app.py
9
- pinned: false
10
  license: mit
11
  short_description: TalkingAIResearcher
12
  ---
@@ -17,4 +17,138 @@ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-
17
  #ANTHROPIC_API_KEY=your_key
18
  #HF_KEY=your_key
19
 
 
20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  sdk: streamlit
7
  sdk_version: 1.41.1
8
  app_file: app.py
9
+ pinned: true
10
  license: mit
11
  short_description: TalkingAIResearcher
12
  ---
 
17
  #ANTHROPIC_API_KEY=your_key
18
  #HF_KEY=your_key
19
 
20
+ Features:
21
 
22
+ 🎯 Core Configuration & Setup
23
+
24
+ Configures Streamlit page with title "🚲BikeAI🏆 Claude/GPT Research"
25
+
26
+
27
+ 🔑 API Setup & Clients
28
+
29
+ Initializes OpenAI, Anthropic, and HuggingFace API clients with environment variables
30
+
31
+
32
+ 📝 Session State Management
33
+
34
+ Manages conversation history, transcripts, file editing states, and model selections
35
+
36
+
37
+ 🧠 get_high_info_terms()
38
+
39
+ Extracts meaningful keywords from text while filtering common stop words
40
+
41
+
42
+ 🏷️ clean_text_for_filename()
43
+
44
+ Sanitizes text to create valid filenames by removing special characters
45
+
46
+
47
+ 📄 generate_filename()
48
+
49
+ Creates intelligent filenames based on content and timestamps
50
+
51
+
52
+ 💾 create_file()
53
+
54
+ Saves prompt and response content to files with smart naming
55
+
56
+
57
+ 🔗 get_download_link()
58
+
59
+ Generates base64-encoded download links for files
60
+
61
+
62
+ 🎤 clean_for_speech()
63
+
64
+ Prepares text for speech synthesis by removing special characters
65
+
66
+
67
+ 🗣️ speech_synthesis_html()
68
+
69
+
70
+ Creates HTML for browser-based speech synthesis
71
+
72
+
73
+ 🔊 edge_tts_generate_audio()
74
+
75
+
76
+ Generates MP3 audio files using Edge TTS
77
+
78
+
79
+ 🎵 speak_with_edge_tts()
80
+
81
+
82
+ Wrapper for Edge TTS audio generation
83
+
84
+
85
+ 🎧 play_and_download_audio()
86
+
87
+
88
+ Creates audio player interface with download option
89
+
90
+
91
+ 📸 process_image()
92
+
93
+
94
+ Analyzes images using GPT-4V
95
+
96
+
97
+ 🎙️ process_audio()
98
+
99
+
100
+ Transcribes audio using Whisper
101
+
102
+
103
+ 🎥 process_video()
104
+
105
+
106
+ Extracts frames from video files
107
+
108
+
109
+ 🤖 process_video_with_gpt()
110
+
111
+
112
+ Analyzes video frames using GPT-4V
113
+
114
+
115
+ 📚 parse_arxiv_refs()
116
+
117
+
118
+ Parses research paper references into structured format
119
+
120
+
121
+ 🔍 perform_ai_lookup()
122
+
123
+
124
+ Searches and processes arXiv papers with audio summaries
125
+
126
+
127
+ 📁 create_zip_of_files()
128
+
129
+
130
+ Bundles multiple files into a zip with smart naming
131
+
132
+
133
+ 📂 load_files_for_sidebar()
134
+
135
+
136
+ Organizes files by timestamp for sidebar display
137
+
138
+
139
+ 🏷️ extract_keywords_from_md()
140
+
141
+
142
+ Pulls keywords from markdown files for organization
143
+
144
+
145
+ 📊 display_file_manager_sidebar()
146
+
147
+
148
+ Creates interactive sidebar for file management
149
+
150
+
151
+ 🎬 main()
152
+
153
+
154
+ Orchestrates overall application flow and UI components