# Project export: Reflectra This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small. ## Project metadata - Hackathon: Cal Hacks 11.0 - Tagline: Our AI journaling tool helps manage life's complexities. It listens, remembers, and engages like a compassionate friend, helping you find clarity by simply talking things through. - Devpost: https://devpost.com/software/reflectra - GitHub: https://github.com/somesh-bagadiya/calhacks11.0 - Team: 4 GitHub contributor(s) — Preetam Maske (10 commits), Harshal Shrimali (9 commits), Somesh Bagadiya (6 commits), Tanmay (1 commits) ## Devpost submission (written by the team) ### Inspiration As Resident Advisors, we often found ourselves juggling numerous responsibilities. Journaling became an essential tool for managing the hidden complexities of our daily tasks. Through journaling, we realized that speaking thoughts aloud often led to clarity and solutions. Inspired by the positive impact of journaling and conversations, we created Reflectra—a digital journaling tool with an AI voice bot that listens, understands, and helps users gain insights. What It Does Reflectra is a digital journaling platform designed to provide a seamless experience for recording thoughts and tasks. Paired with an AI voice bot, Reflectra goes beyond traditional journaling by engaging users in meaningful conversations. The AI remembers previous entries, enabling personalized interactions that guide users to reflect, problem-solve, and find clarity. It functions like a compassionate companion, encouraging self-reflection and emotional support through dialogue. How We Built It Journaling Platform: We developed a simple and intuitive interface using Reflex, allowing users to jot down their thoughts effortlessly. Reflex provided a streamlined way to build the platform with pure Python code. Aura Voice Bot: The voice bot was built using tools from fetch.ai, Deepgram, and OpenAI. When a user records a journal entry, the system creates a vector database using ChromaDB and sends the data to OpenAI to generate thoughtful, personalized responses. This AI-driven interaction makes Reflectra feel more personal and engaging, providing meaningful conversations tailored to the user's journaling history. Challenges We Faced User Experience Design: One of the biggest challenges was creating an interface that balances simplicity with rich functionality, allowing users to log thoughts easily while still experiencing deep AI interactions. Privacy and Security: Protecting user data was critical. Ensuring that personal thoughts were securely stored while maintaining a smooth experience required rigorous security measures. Empathy in AI: Fine-tuning the AI to deliver empathetic and emotionally intelligent responses was particularly challenging. We had to carefully adjust the language model to create a warm, supportive tone. Accomplishments We’re Proud Of Meaningful User Experience: Reflectra offers more than just task management; it supports users emotionally, helping them feel understood and organized. AI Integration in Real-Life Applications: The AI voice bot isn't just a gimmick—it actively engages users, facilitating thoughtful reflection and problem-solving. Data Security: We successfully implemented strong security protocols, ensuring that users' private data remains confidential while providing a smooth journaling experience. What We Learned The Value of Journaling: Keeping track of daily tasks and thoughts can significantly improve decision-making and emotional well-being. Empathy in AI Design: Developing AI that can communicate in a compassionate and engaging way is challenging but incredibly rewarding. Balancing Simplicity with Functionality: Providing advanced features while keeping the interface user-friendly is crucial to the overall user experience. What’s Next for Reflectra Enhanced AI Capabilities: We aim to improve Reflectra’s natural language understanding, making conversations even more insightful and personalized. Mobile App Development: To increase accessibility, we’re working on a mobile version of the platform, ensuring that users can reflect on the go. Personalized Insights: We plan to leverage data analysis to provide users with personalized insights based on their journaling patterns, helping them grow over time. Integration with Mental Health Tools: Reflectra will evolve into a mental well-being tool by integrating with existing wellness apps, offering emotional support as part of users' daily routines. Reflectra is more than just a digital diary; it’s a personal companion that helps users navigate life’s complexities with clarity and emotional support. Through Reflectra, we hope to make journaling an insightful and empowering experience for everyone. ## README (from the GitHub repository) # Reflectra ![image](https://github.com/user-attachments/assets/e78d1724-4bbc-4c43-bfef-bf3a57539d18) ## Detected evidence (automated analysis) Indexed codebase: 28 recognized source files, 105 KB. - FastAPI (technology) — detected in the code - OpenAI (technology) — detected in the code - Python (language) — detected in the code - Redis (technology) — detected in the code ## Codebase structure (from repository index) ### Files (39 of 39) ``` .gitignore environment.yml fetch_agents/.gitignore fetch_agents/20241020_030028.txt fetch_agents/20241020_030205.txt fetch_agents/20241020_030329.txt fetch_agents/analyze_mood.py fetch_agents/display_agent.py fetch_agents/index.py fetch_agents/openai_function.py fetch_agents/readme.md fetch_agents/recordAudio.py fetch_agents/recording_agent.py fetch_agents/redis_agent.py fetch_agents/requirements.txt fetch_agents/sender_agent.py fetch_agents/summary_agent.py fetch_agents/transcribeAgent.py fetch_agents/transcription_agent.py frontend/reflex-app/.gitignore frontend/reflex-app/diary_vectordb/chroma.sqlite3 frontend/reflex-app/reflex_app/__init__.py frontend/reflex-app/reflex_app/backend/__init__.py frontend/reflex-app/reflex_app/backend/data/embedding_generated/Day 1.txt frontend/reflex-app/reflex_app/backend/diary_vectordb/chroma.sqlite3 frontend/reflex-app/reflex_app/backend/RAGImplemented.py frontend/reflex-app/reflex_app/backend/redis.py frontend/reflex-app/reflex_app/backend/STT_script.py frontend/reflex-app/reflex_app/pages/__init__.py frontend/reflex-app/reflex_app/pages/calendar.py frontend/reflex-app/reflex_app/pages/calendarTodo.py frontend/reflex-app/reflex_app/pages/journalPage.py frontend/reflex-app/reflex_app/pages/login.py frontend/reflex-app/reflex_app/pages/signup.py frontend/reflex-app/reflex_app/pages/todoList.py frontend/reflex-app/reflex_app/reflex_app.py frontend/reflex-app/requirements.txt frontend/reflex-app/rxconfig.py README.md ``` ### Dependencies - fetch_agents/requirements.txt: aenum@==3.1.15, aiofiles@==24.1.0, aiohappyeyeballs@==2.4.3, aiohttp@==3.10.9, aiosignal@==1.3.1, alembic@==1.13.3, altair@==5.4.1, annotated-types@==0.7.0, anyio@==4.6.2.post1, apispec@==6.6.1, attrs@==24.2.0, bech32@==1.2.0, bidict@==0.23.1, blinker@==1.8.2, build@==1.2.2.post1, cachetools@==5.5.0, certifi@==2024.8.30, cffi@==1.17.1, charset-normalizer@==3.4.0, click@==8.1.7, cosmpy@==0.9.2, dataclasses-json@==0.6.7, deepgram-sdk, deprecation@==2.1.0, distro@==1.9.0, docutils@==0.21.2, ecdsa@==0.19.0, fastapi@==0.115.2, filelock@==3.16.1, frozenlist@==1.4.1, fsspec@==2024.9.0, gitdb@==4.0.11, GitPython@==3.1.43, googleapis-common-protos@==1.65.0, grpcio@==1.66.2, gunicorn@==23.0.0, h11@==0.14.0, httpcore@==1.0.6, httpx@==0.27.2, huggingface-hub@==0.26.0, idna@==3.10, importlib_metadata@==8.5.0, jaraco.classes@==3.4.0, jaraco.context@==6.0.1, jaraco.functools@==4.1.0, Jinja2@==3.1.4, jiter@==0.6.1, jsonschema@==4.23.0, jsonschema-specifications@==2024.10.1, keyring@==25.4.1, lazy_loader@==0.4, Mako@==1.3.5, markdown-it-py@==3.0.0, MarkupSafe@==3.0.2, marshmallow@==3.23.0, mdurl@==0.1.2, more-itertools@==10.5.0, mpmath@==1.3.0, msgpack@==1.1.0, multidict@==6.1.0, mypy-extensions@==1.0.0, narwhals@==1.9.4, networkx@==3.4.1, nh3@==0.2.18, numpy@==2.1.2, openai@==1.52.0, packaging@==24.1, pandas@==2.2.3, pillow@==10.4.0, pipdeptree@==2.16.2, pkginfo@==1.10.0, platformdirs@==4.3.6, propcache@==0.2.0, protobuf@==4.25.5, psutil@==6.1.0, pyarrow@==17.0.0, PyAudio@==0.2.14, pycparser@==2.22, pycryptodome@==3.21.0, pydantic@==2.8.2, pydantic_core@==2.20.1, pydeck@==0.9.1, Pygments@==2.18.0, pyproject_hooks@==1.2.0, python-dateutil@==2.9.0.post0, python-engineio@==4.10.1, python-multipart@==0.0.12, python-socketio@==5.11.4, pytz@==2024.2, PyYAML@==6.0.2, readme_renderer@==44.0, redis@==5.1.1, referencing@==0.35.1, regex@==2024.9.11, requests@==2.32.3, requests-toolbelt@==1.0.0, rfc3986@==2.0.0, rich@==13.9.2, rpds-py@==0.20.0, safetensors@==0.4.5, scipy, setuptools@==75.2.0, shellingham@==1.5.4, simple-websocket@==1.1.0, six@==1.16.0, smmap@==5.0.1, sniffio@==1.3.1, sounddevice@==0.5.1, soundfile@==0.12.1, SQLAlchemy@==2.0.36, sqlmodel@==0.0.22, starlette@==0.40.0, starlette-admin@==0.14.1, sympy@==1.13.1, tabulate@==0.9.0, tenacity@==9.0.0, tokenizers@==0.20.1, toml@==0.10.2, tomlkit@==0.13.2, tornado@==6.4.1, tqdm@==4.66.5, twine@==5.1.1, typer@==0.12.5, typing_extensions@==4.12.2, typing-inspect@==0.9.0, tzdata@==2024.2, uagents@==0.16.2, urllib3@==2.2.3, uvicorn@==0.30.6, websockets, wheel@==0.44.0, wrapt@==1.16.0, wsproto@==1.2.0, yarl@==1.14.0, zipp@==3.20.2 ### Recent commits (newest first) - Merge pull request #4 from somesh-bagadiya/fetch-workflow - All done - Merge pull request #3 from somesh-bagadiya/fetch-workflow - Update README.md - Update README.md - theme & sound - Backend frontend - color scheme changed - workflow after mic pressed - Merge branch 'fronend' into fetch-workflow - read tasks from redis - rag - Merge branch 'fetch-workflow' of https://github.com/somesh-bagadiya/calhacks11.0 into fetch-workflow - Merge branch 'fetch-workflow' of https://github.com/somesh-bagadiya/calhacks11.0 into fetch-workflow - working fetch - date with redis - Merge pull request #2 from somesh-bagadiya/fronend - Merge pull request #1 from somesh-bagadiya/fetch-workflow - Update requirements.txt - trancribe function ## Key source files (fetched from GitHub, selected and truncated for size) ### fetch_agents/requirements.txt ``` aenum==3.1.15 aiofiles==24.1.0 aiohappyeyeballs==2.4.3 aiohttp==3.10.9 aiosignal==1.3.1 alembic==1.13.3 altair==5.4.1 annotated-types==0.7.0 anyio==4.6.2.post1 apispec==6.6.1 attrs==24.2.0 bech32==1.2.0 bidict==0.23.1 blinker==1.8.2 build==1.2.2.post1 cachetools==5.5.0 certifi==2024.8.30 cffi==1.17.1 charset-normalizer==3.4.0 click==8.1.7 cosmpy==0.9.2 dataclasses-json==0.6.7 deepgram-sdk deprecation==2.1.0 distro==1.9.0 docutils==0.21.2 ecdsa==0.19.0 fastapi==0.115.2 filelock==3.16.1 frozenlist==1.4.1 fsspec==2024.9.0 gitdb==4.0.11 GitPython==3.1.43 googleapis-common-protos==1.65.0 grpcio==1.66.2 gunicorn==23.0.0 h11==0.14.0 httpcore==1.0.6 httpx==0.27.2 huggingface-hub==0.26.0 idna==3.10 importlib_metadata==8.5.0 jaraco.classes==3.4.0 jaraco.context==6.0.1 jaraco.functools==4.1.0 Jinja2==3.1.4 jiter==0.6.1 jsonschema==4.23.0 jsonschema-specifications==2024.10.1 keyring==25.4.1 lazy_loader==0.4 Mako==1.3.5 markdown-it-py==3.0.0 MarkupSafe==3.0.2 marshmallow==3.23.0 mdurl==0.1.2 more-itertools==10.5.0 mpmath==1.3.0 msgpack==1.1.0 multidict==6.1.0 mypy-extensions==1.0.0 narwhals==1.9.4 networkx==3.4.1 nh3==0.2.18 numpy==2.1.2 openai==1.52.0 packaging==24.1 pandas==2.2.3 pillow==10.4.0 pipdeptree==2.16.2 pkginfo==1.10.0 platformdirs==4.3.6 propcache==0.2.0 protobuf==4.25.5 psutil==6.1.0 pyarrow==17.0.0 PyAudio==0.2.14 pycparser==2.22 pycryptodome==3.21.0 pydantic==2.8.2 pydantic_core==2.20.1 pydeck==0.9.1 Pygments==2.18.0 pyproject_hooks==1.2.0 python-dateutil==2.9.0.post0 python-engineio==4.10.1 python-multipart==0.0.12 python-socketio==5.11.4 pytz==2024.2 PyYAML==6.0.2 readme_renderer==44.0 redis==5.1.1 referencing==0.35.1 regex==2024.9.11 requests==2.32.3 requests-toolbelt==1.0.0 rfc3986==2.0.0 rich==13.9.2 rpds-py==0.20.0 safetensors==0.4.5 scipy setuptools==75.2.0 shellingham==1.5.4 simple-websocket==1.1.0 six==1.16.0 smmap==5.0.1 sniffio==1.3.1 sounddevice==0.5.1 soundfile==0.12.1 SQLAlchemy==2.0.36 sqlmodel==0.0.22 starlette==0.40.0 starlette-admin==0.14.1 sympy==1.13.1 tabulate==0.9.0 tenacity==9.0.0 tokenizers==0.20.1 toml==0.10.2 tomlkit==0.13.2 tornado==6.4.1 tqdm==4.66.5 twine==5.1.1 typer==0.12.5 typing-inspect==0.9.0 typing_extensions==4.12.2 tzdata==2024.2 websockets uagents==0.16.2 urllib3==2.2.3 uvicorn==0.30.6 wheel==0.44.0 wrapt==1.16.0 wsproto==1.2.0 yarl==1.14.0 zipp==3.20.2 ``` ### frontend/reflex-app/requirements.txt ``` ��alembic==1.13.3 annotated-types==0.7.0 anyio==4.6.2.post1 bidict==0.23.1 black==24.10.0 build==1.2.2.post1 certifi==2024.8.30 charset-normalizer==3.4.0 click==8.1.7 colorama==0.4.6 docutils==0.21.2 fastapi==0.115.2 gunicorn==23.0.0 h11==0.14.0 httpcore==1.0.6 httpx==0.27.2 idna==3.10 importlib_metadata==8.5.0 jaraco.classes==3.4.0 jaraco.context==6.0.1 jaraco.functools==4.1.0 Jinja2==3.1.4 keyring==25.4.1 lazy_loader==0.4 Mako==1.3.5 markdown-it-py==3.0.0 MarkupSafe==3.0.2 mdurl==0.1.2 more-itertools==10.5.0 mypy-extensions==1.0.0 nh3==0.2.18 packaging==24.1 pathspec==0.12.1 pipdeptree==2.16.2 pkginfo==1.10.0 platformdirs==4.3.6 psutil==6.1.0 pydantic==2.9.2 pydantic_core==2.23.4 Pygments==2.18.0 pyproject_hooks==1.2.0 python-dateutil==2.9.0.post0 python-engineio==4.10.1 python-multipart==0.0.12 python-socketio==5.11.4 pywin32-ctypes==0.2.3 readme_renderer==44.0 redis==5.1.1 reflex==0.6.3 reflex-chakra==0.6.2 reflex-hosting-cli==0.1.13 requests==2.32.3 requests-toolbelt==1.0.0 rfc3986==2.0.0 rich==13.9.2 setuptools==75.2.0 shellingham==1.5.4 simple-websocket==1.1.0 six==1.16.0 sniffio==1.3.1 SQLAlchemy==2.0.36 sqlmodel==0.0.22 starlette==0.40.0 starlette-admin==0.14.1 tabulate==0.9.0 tomlkit==0.13.2 twine==5.1.1 typer==0.12.5 typing_extensions==4.12.2 urllib3==2.2.3 uvicorn==0.32.0 websockets==13.1 wheel==0.44.0 wrapt==1.16.0 wsproto==1.2.0 zipp==3.20.2 ``` ### fetch_agents/index.py ```python import subprocess import os def run_reverse_workflow(): # Activate virtual environment venv_path = "./venv/bin/activate" if os.name == 'nt': venv_path = "./venv/Scripts/activate" activate_command = f"source {venv_path} && " if os.name != 'nt' else f"{venv_path} && " # Workflow defined in reverse order workflow = [ "redis_agent.py", "summary_agent.py", "display_agent.py", "transcribing_agent.py", "recording_agent.py", "sender_agent.py" ] # Run each Python file in reverse order within the virtual environment for agent in workflow: print(f"Running {agent}...") subprocess.run(f"{activate_command} python {agent}", shell=True, executable='/bin/bash') # Execute the function run_reverse_workflow() ``` ### environment.yml ```yaml ��name: integration_env channels: - bioconda - nvidia - anaconda - defaults dependencies: - alabaster=0.7.16=py312haa95532_0 - arrow=1.3.0=py312haa95532_0 - astroid=2.14.2=py312haa95532_0 - asttokens=2.0.5=pyhd3eb1b0_0 - atomicwrites=1.4.0=py_0 - attrs=24.2.0=py312haa95532_0 - autopep8=2.0.4=pyhd3eb1b0_0 - babel=2.11.0=py312haa95532_0 - bcrypt=3.2.0=py312h2bbff1b_1 - beautifulsoup4=4.12.3=py312haa95532_0 - binaryornot=0.4.4=pyhd3eb1b0_1 - black=24.8.0=py312haa95532_0 - bleach=4.1.0=pyhd3eb1b0_0 - brotli-python=1.0.9=py312hd77b12b_8 - bzip2=1.0.8=h2bbff1b_6 - ca-certificates=2024.9.24=haa95532_0 - certifi=2024.8.30=py312haa95532_0 - cffi=1.17.1=py312h827c3e9_0 - chardet=4.0.0=py312haa95532_1003 - charset-normalizer=3.3.2=pyhd3eb1b0_0 - click=8.1.7=py312haa95532_0 - cloudpickle=3.0.0=py312haa95532_0 - colorama=0.4.6=py312haa95532_0 - comm=0.2.1=py312haa95532_0 - cookiecutter=2.6.0=py312haa95532_0 - cryptography=43.0.0=py312h89fc84f_0 - debugpy=1.6.7=py312hd77b12b_0 - decorator=5.1.1=pyhd3eb1b0_0 - defusedxml=0.7.1=pyhd3eb1b0_0 - diff-match-patch=20200713=pyhd3eb1b0_0 - dill=0.3.8=py312haa95532_0 - docstring-to-markdown=0.11=py312haa95532_0 - executing=0.8.3=pyhd3eb1b0_0 - expat=2.6.3=h5da7b33_0 - flake8=7.0.0=py312haa95532_0 - icu=73.1=h6c2663c_0 - idna=3.7=py312haa95532_0 - imagesize=1.4.1=py312haa95532_0 - importlib-metadata=7.0.1=py312haa95532_0 - inflection=0.5.1=py312haa95532_1 - intervaltree=3.1.0=pyhd3eb1b0_0 - ipykernel=6.29.5=py312haa95532_0 - ipython=8.27.0=py312haa95532_0 - isort=5.13.2=py312haa95532_0 - jaraco.classes=3.2.1=pyhd3eb1b0_0 - jedi=0.19.1=py312haa95532_0 - jellyfish=1.0.1=py312h36a85e1_0 - jinja2=3.1.4=py312haa95532_0 - jpeg=9e=h827c3e9_3 - jsonschema=4.23.0=py312haa95532_0 - jsonschema-specifications=2023.7.1=py312haa95532_0 - jupyter_client=8.6.0=py312haa95532_0 - jupyter_core=5.7.2=py312haa95532_0 - jupyterlab_pygments=0.2.2=py312haa95532_0 - keyring=24.3.1=py312haa95532_0 - krb5=1.20.1=h5b6d351_1 - lazy-object-proxy=1.10.0=py312h2bbff1b_0 - libclang=14.0.6=default_hb5a9fac_1 - libclang13=14.0.6=default_h8e68704_1 - libffi=3.4.4=hd77b12b_1 - libpng=1.6.39=h8cc25b3_0 - libpq=12.17=h906ac69_0 - libsodium=1.0.18=h62dcd97_0 - libspatialindex=1.9.3=h6c2663c_0 - lz4-c=1.9.4=h2bbff1b_1 - markdown-it-py=2.2.0=py312haa95532_1 - markupsafe=2.1.3=py312h2bbff1b_0 - matplotlib-inline=0.1.6=py312haa95532_0 - mccabe=0.7.0=pyhd3eb1b0_0 - mdurl=0.1.0=py312haa95532_0 - mistune=2.0.4=py312haa95532_0 - more-itertools=10.3.0=py312haa95532_0 - mypy_extensions=1.0.0=py312haa95532_0 - nbclient=0.8.0=py312haa95532_0 - nbconvert=7.16.4=py312haa95532_0 - nbformat=5.10.4=py312haa95532_0 - nest-asyncio=1.6.0=py312haa95532_0 - numpydoc=1.7.0=py312haa95532_0 - openssl=3.0.15=h827c3e9_0 - packaging=24.1=p [truncated — 9830 more characters] ``` ### fetch_agents/analyze_mood.py ```python import openai import os from openai import OpenAI # Automatically gets API Key from environment variable OPENAI_API_KEY openai.api_key = os.getenv("OPENAI_API_KEY") client = OpenAI() # Journal entry transcript = "I had a really busy day today, and it left me feeling a bit overwhelmed, but I also felt accomplished after finishing all my tasks." # Create a completion request using the chat completion API completion = client.chat.completions.create( model="gpt-3.5-turbo", # Correct model name messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Analyze the following text from a daily journal entry and determine the mood of the user: in stressed, happy, sad, excited, neutral"}, {"role": "user", "content": f"{transcript}"} ] ) print(completion.choices[0].message.content) # Extract and print the mood from the response mood = completion.choices[0].message.content # print(f"Detected Mood: {mood}") # print(mood) ``` ### fetch_agents/redis_agent.py ```python from uagents import Agent, Model, Context # from recordAudio import transcribe_audio from uagents.setup import fund_agent_if_low import datetime from datetime import date # import openai_function from datetime import datetime from typing import List class RedisMessage(Model): summary:str date : date mood : str transcript_list : List[str] # Create the transcription agent redis_agent = Agent( name="redis_agent", seed="redis_agent_seed", port=8006, endpoint=['http://localhost:8006/submit'] ) fund_agent_if_low(redis_agent.wallet.address()) print(f"redis Agent Address: {redis_agent.address}") # Handler for incoming audio file messages in the transcription agent @redis_agent.on_message(model=RedisMessage) async def handle_audio_file_message(ctx: Context, sender: str, msg: RedisMessage): print(f"[Redis Agent] Received audio file path from {sender}") print(f'q1 - {msg.transcript_list[0]}') print(f'q2 - {msg.transcript_list[1]}') print(f'mood - {msg.mood}') print(f'date - {msg.date}') print(f'summary - {msg.summary}') # Print the transcription agent's addresss print(f"Redis Agent Address: {redis_agent.address}") if __name__ == "__main__": redis_agent.run() ``` ### fetch_agents/transcription_agent.py ```python from uagents import Agent, Model, Context from recordAudio import transcribe_audio from uagents.setup import fund_agent_if_low # Define the message models class AudioFileMessage(Model): filepath: str idx: int class TranscriptionMessage(Model): transcription: str idx: int # Create the transcription agent transcription_agent = Agent( name="transcription_agent", seed="transcription_agent_seed", port=8003, endpoint=['http://localhost:8003/submit'] ) fund_agent_if_low(transcription_agent.wallet.address()) # Handler for incoming audio file messages in the transcription agent @transcription_agent.on_message(model=AudioFileMessage) async def handle_audio_file_message(ctx: Context, sender: str, msg: AudioFileMessage): print(f"[Transcription Agent] Received audio file path from {sender}") # Transcribe the audio file transcription = await transcribe_audio(msg.filepath) # Send the transcription to the display agent using its address await ctx.send("agent1q278jzg45mrcqm5g5lkgyk66j7cs9nsvxf6xu8u0q0sedln3w27ngmua7se", TranscriptionMessage(transcription=transcription, idx=msg.idx)) # Print the transcription agent's address print(f"Transcription Agent Address: {transcription_agent.address}") if __name__ == "__main__": transcription_agent.run() ``` ### fetch_agents/sender_agent.py ```python from uagents import Agent, Model, Context from uagents.setup import fund_agent_if_low # Define the message models class StartRecordingMessage(Model): question: str idx: int # Define the message models class RecordAudioMessage(Model): question: str idx: int duration: int # Create the sender agent sender_agent = Agent( name="sender_agent", seed="sender_agent_seed", port=8001, endpoint=['http://localhost:8001/submit'] ) fund_agent_if_low(sender_agent.wallet.address()) JOURNALING_QUESTIONS = [ "How was your day?", "What challenges did you face today?" ] journaling_started = False # Handler in the sender agent to start the journaling process @sender_agent.on_interval(period=30.0) # Set the interval to start asking questions async def start_journaling(ctx: Context): global journaling_started if journaling_started: return # Exit if the journaling has already started journaling_started = True for idx, question in enumerate(JOURNALING_QUESTIONS, start=1): print(f"Sending question {idx}: {question}") # Send a RecordAudioMessage to the recording agent # todo connect front end await ctx.send("agent1qgr68mdea9paflx0te4ljyztjfxaj5fxgj6rgs55pk4nhfpc8ru7y3t8lav", RecordAudioMessage(question=question, idx=idx, duration=5)) # Print the sender agent's address print(f"Sender Agent Address: {sender_agent.address}") if __name__ == "__main__": sender_agent.run() ``` ### fetch_agents/summary_agent.py ```python from uagents import Agent, Model, Context # from recordAudio import transcribe_audio from uagents.setup import fund_agent_if_low import datetime from datetime import date import openai_function from datetime import datetime from typing import List class SummaryMessage(Model): summary : str mood : str transcript_list : List[str] class RedisMessage(Model): summary:str date : date mood : str transcript_list : List[str] # Create the transcription agent summary_agent = Agent( name="summary_agent", seed="summary_agent_seed", port=8005, endpoint=['http://localhost:8005/submit'] ) fund_agent_if_low(summary_agent.wallet.address()) print(f"summary Agent Address: {summary_agent.address}") # Handler for incoming audio file messages in the transcription agent @summary_agent.on_message(model=SummaryMessage) async def handle_audio_file_message(ctx: Context, sender: str, msg: SummaryMessage): print(f"[Summary Agent] Received a SummaryMessage type from {sender}") # Transcribe the audio file summary = openai_function.summarize_journal(msg.summary) print(f"Summary of today's journal: {summary}") await ctx.send("agent1qw30j7c7x2p6evel4jag89tpldtkzql97gz7pr8vlczgzf28ww5nuwy5ngt", RedisMessage(transcript_list = msg.transcript_list, summary=summary, date = date.today(), mood = msg.mood)) # Print the transcription agent's addresss print(f"Summary Agent Address: {summary_agent.address}") if __name__ == "__main__": summary_agent.run() ``` ### fetch_agents/recording_agent.py ```python import os from uagents import Agent, Model, Context import asyncio from recordAudio import record_audio from uagents.setup import fund_agent_if_low # Define the message models class RecordAudioMessage(Model): question: str idx: int duration: int class AudioFileMessage(Model): filepath: str idx: int # Create the recording agent recording_agent = Agent( name="recording_agent", seed="recording_agent_seed", port=8002, endpoint=['http://localhost:8002/submit'] ) fund_agent_if_low(recording_agent.wallet.address()) # Handler in the recording agent to record audio @recording_agent.on_message(model=RecordAudioMessage) async def handle_record_audio(ctx: Context, sender: str, msg: RecordAudioMessage): print(f"\nRecording for Question {msg.idx}: {msg.question}") # input("Press Enter when you're ready to record...") # Record the audio filename = f"response_{msg.idx}.wav" duration = msg.duration # Run the blocking recording in an executor loop = asyncio.get_event_loop() await loop.run_in_executor(None, record_audio, duration, filename) # Check if the audio file exists if not os.path.exists(filename): print(f"Audio file {filename} not found.") return # Send the audio file message to the transcription agent using its address await ctx.send("agent1qt9ymdhph4luhj83qajjpgmvz7p7h88ddxjtwchyagvgta3dghdk55jf5zu", AudioFileMessage(filepath=filename, idx=msg.idx)) # Print the recording agent's address print(f"Recording Agent Address: {recording_agent.address}") if __name__ == "__main__": recording_agent.run() ``` [17 more indexed source files omitted to keep this export small. The full file list is in the Codebase structure section above.]