├── requirements.txt ├── README.md ├── LICENSE ├── test.py ├── app.py └── .gitignore /requirements.txt: -------------------------------------------------------------------------------- 1 | streamlit 2 | requests 3 | python-dotenv 4 | openai 5 | gpt_index==0.4.15 6 | langchain==0.0.96 7 | PyPDF2 8 | chromadb -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Chat-with-Audio-using-LLM 2 | This is a Streamlit application that helps you chat with your audio file powered by Langchain, ChromaDB, and OpenAI. 3 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2023 AI Anytime 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /test.py: -------------------------------------------------------------------------------- 1 | import streamlit as st 2 | import json 3 | import os 4 | import time 5 | from dotenv import load_dotenv 6 | import requests 7 | 8 | load_dotenv() 9 | api_token = os.getenv('ASSEMBLY_AI_KEY') 10 | 11 | base_url = "https://api.assemblyai.com/v2" 12 | 13 | headers = { 14 | "authorization": api_token, 15 | "content-type": "application/json" 16 | } 17 | 18 | 19 | 20 | def assemblyai_stt(url): 21 | data = { 22 | "audio_url": url # You can also use a URL to an audio or video file on the web 23 | } 24 | url = base_url + "/transcript" 25 | response = requests.post(url, json=data, headers=headers) 26 | transcript_id = response.json()['id'] 27 | return transcript_id 28 | 29 | 30 | #Assembly AI LLM Code 31 | transcript_id = "transcript_id" 32 | 33 | def post_lemur(transcript_id, query): 34 | url = "https://api.assemblyai.com/v2/generate/question-answer" 35 | 36 | questions = [ 37 | { 38 | "question": query, 39 | "answer_format": "Short sentence" 40 | }] 41 | 42 | data = { 43 | "transcript_ids": [transcript_id], 44 | "questions": questions 45 | } 46 | 47 | response = requests.post(url, json=data, headers=headers) 48 | return response 49 | 50 | #Streamlit Code 51 | st.set_page_config(layout="wide", page_title="ChatAudio", page_icon="🔊") 52 | 53 | st.title("Chat with Your Audio using LLM") 54 | 55 | input_source = st.text_input("Enter the YouTube video URL") 56 | 57 | if input_source is not None: 58 | col1, col2 = st.columns(2) 59 | 60 | with col1: 61 | st.info("Your uploaded video") 62 | st.video(input_source) 63 | transription_id = assemblyai_stt(input_source) 64 | #st.info(transription_id) 65 | with col2: 66 | st.info("Chat Below") 67 | query = st.text_area("Ask your Query here...") 68 | if query is not None: 69 | if st.button("Ask"): 70 | st.info("Your Query is: " + query) 71 | lemur_output = post_lemur(transcript_id, query) 72 | lemur_response = lemur_output.json() 73 | st.success(lemur_response) 74 | 75 | 76 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | import streamlit as st 2 | import json 3 | import os 4 | import time 5 | import sys 6 | from dotenv import load_dotenv 7 | import requests 8 | from pytube import YouTube 9 | from pathlib import Path 10 | from langchain.document_loaders import TextLoader 11 | from langchain.indexes import VectorstoreIndexCreator 12 | 13 | load_dotenv() 14 | api_token = os.getenv('ASSEMBLY_AI_KEY') 15 | os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY') 16 | 17 | base_url = "https://api.assemblyai.com/v2" 18 | 19 | headers = { 20 | "authorization": api_token, 21 | "content-type": "application/json" 22 | } 23 | 24 | # PyTube function for YouTube video 25 | def save_audio(url): 26 | yt = YouTube(url) 27 | video = yt.streams.filter(only_audio=True).first() 28 | out_file = video.download() 29 | base, ext = os.path.splitext(out_file) 30 | file_name = base + '.mp3' 31 | try: 32 | os.rename(out_file, file_name) 33 | except WindowsError: 34 | os.remove(file_name) 35 | os.rename(out_file, file_name) 36 | audio_filename = Path(file_name).stem+'.mp3' 37 | return audio_filename 38 | 39 | # Assembly AI speech to text 40 | def assemblyai_stt(audio_filename): 41 | with open(audio_filename , "rb") as f: 42 | response = requests.post(base_url + "/upload", 43 | headers=headers, 44 | data=f) 45 | 46 | upload_url = response.json()["upload_url"] 47 | data = { 48 | "audio_url": upload_url 49 | } 50 | url = base_url + "/transcript" 51 | response = requests.post(url, json=data, headers=headers) 52 | transcript_id = response.json()['id'] 53 | polling_endpoint = f"https://api.assemblyai.com/v2/transcript/{transcript_id}" 54 | 55 | while True: 56 | transcription_result = requests.get(polling_endpoint, headers=headers).json() 57 | 58 | if transcription_result['status'] == 'completed': 59 | break 60 | 61 | elif transcription_result['status'] == 'error': 62 | raise RuntimeError(f"Transcription failed: {transcription_result['error']}") 63 | 64 | else: 65 | print("Processing...") 66 | time.sleep(3) 67 | print(transcription_result['text']) 68 | file = open('docs/transcription.txt', 'w') 69 | file.write(transcription_result['text']) 70 | file.close() 71 | return transcription_result['text'] 72 | 73 | # Open AI code 74 | def langchain_qa(query): 75 | loader = TextLoader('docs/transcription.txt') 76 | index = VectorstoreIndexCreator().from_loaders([loader]) 77 | query = query 78 | result = index.query(query) 79 | return result 80 | 81 | 82 | #Streamlit Code 83 | st.set_page_config(layout="wide", page_title="ChatAudio", page_icon="🔊") 84 | 85 | st.title("Chat with Your Audio using LLM") 86 | 87 | input_source = st.text_input("Enter the YouTube video URL") 88 | 89 | if input_source is not None: 90 | col1, col2 = st.columns(2) 91 | 92 | with col1: 93 | st.info("Your uploaded video") 94 | st.video(input_source) 95 | audio_filename = save_audio(input_source) 96 | transription = assemblyai_stt(audio_filename) 97 | st.info(transription) 98 | with col2: 99 | st.info("Chat Below") 100 | query = st.text_area("Ask your Query here...") 101 | if query is not None: 102 | if st.button("Ask"): 103 | st.info("Your Query is: " + query) 104 | result = langchain_qa(query) 105 | st.success(result) 106 | 107 | 108 | 109 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | --------------------------------------------------------------------------------