Merge pull request #2 from ZTatman/feat/phase-1-backend-restructure

Restructure into backend/ and fix module import side effects
This commit is contained in:
Zach Tatman 2026-03-18 23:02:42 -04:00 • committed by GitHub
commit d31c28b0ea
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 148 additions and 94 deletions

20
.claude/launch.json Normal file
View file

@ -0,0 +1,20 @@
{
"version": "0.0.1",
"configurations": [
{
"name": "FastAPI backend",
"runtimeExecutable": "uv",
"runtimeArgs": [
"run",
"uvicorn",
"backend.main:app",
"--reload",
"--host",
"0.0.0.0",
"--port",
"8000"
],
"port": 8000
}
]
}

19
backend/db.py Normal file
View file

@ -0,0 +1,19 @@
from functools import lru_cache
from pathlib import Path
import chromadb
_DB_PATH = str(Path(__file__).parent / "chroma_db")
@lru_cache(maxsize=1)
def get_diary_collection():
"""Retrieves diary chromadb collection by either retrieving one that was already created or by creating a new one
Returns:
A chromadb collection with the name "diary"
"""
client = chromadb.PersistentClient(_DB_PATH)
return client.get_or_create_collection(
name="diary", metadata={"hnsw:space": "cosine"}
)

View file

@ -1,8 +1,3 @@
import openai
import streamlit
def main():
print("Hello from nadir!")

91
backend/query.py Normal file
View file

@ -0,0 +1,91 @@
from functools import lru_cache
from db import get_diary_collection
from dotenv import load_dotenv
from openai import OpenAI
model = "llama3.2"
@lru_cache(maxsize=1)
def get_openai_client():
"""Loads environement variables and creates a cached OpenAI client.
Returns:
An OpenAI client
"""
load_dotenv()
client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")
return client
def query_entries(user_question: str) -> str:
"""Query the diary entries using RAG and return an AI-generated answer.
Args:
user_question: The question to ask about emotional patterns
Returns:
A string response from the AI based on relevant diary entries
"""
# create openai client and connect to chromadb
client = get_openai_client()
collection = get_diary_collection()
n = min(3, collection.count())
if n == 0:
return "No diary entries found. Record some entries first."
# ── 1. Retrieve relevant entries from ChromaDB ────────────────────
results = collection.query(query_texts=[user_question], n_results=n)
documents = results["documents"][0]
metadatas = results["metadatas"][0]
# ── 2. Build context string ────────────────────────────────────────
context = ""
for doc, meta in zip(documents, metadatas, strict=True):
moods = meta.get("moods", "unknown") or "unknown"
tags = meta.get("tags", "none") or "none"
context += (
f"Date: {meta.get('date', 'unknown')} | Moods: {moods} | Tags: {tags}\n"
)
context += f"Entry: {doc}\n\n"
# ── 3. Build prompt ────────────────────────────────────────────────
prompt = f"""
You are a warm, concise journaling assistant.
Answer in 1-2 sentences maximum.
Always end by asking if the user wants to explore further.
Use only the journal entries below — do not invent details.
Journal entries:
{context}
Question: {user_question}
"""
# ── 4. Send to model and return response ──────────────────────────
try:
response = client.with_options(timeout=30.0).chat.completions.create(
model=model, messages=[{"role": "user", "content": prompt}]
)
except (APITimeoutError, APIConnectionError):
return "I couldn't reach the local model right now. Please try again."
return (response.choices[0].message.content or "").strip()
if __name__ == "__main__":
# Interactive CLI loop for testing
try:
user_question = input(
"Ask a question about your emotional patterns (q to quit): "
).strip()
while True:
if user_question.lower() == "q":
break
print("\n\n" + query_entries(user_question))
user_question = input("\nAsk another question (q to quit): ").strip()
finally:
print("Chat ended...")

View file

@ -1,11 +1,12 @@
import uuid
from datetime import datetime
from db import get_collection
from db import get_diary_collection
from models import JournalEntry, MoodTag
# from pydantic import BaseModel
collection = get_collection()
collection = get_diary_collection()
def add_entry(transcript: str, moods: list[MoodTag], tags: list[str]):
@ -33,17 +34,18 @@ def add_entry(transcript: str, moods: list[MoodTag], tags: list[str]):
collection.add(ids=[entry.id], documents=[entry.transcript], metadatas=[metadata])
# Test voice entry
add_entry(
transcript=(
"Feeling pretty scattered today. Work was overwhelming and I "
"snapped at a colleague over something small. Didn't sleep well "
"last night and skipped lunch which always makes things worse."
),
moods=[
MoodTag(name="irritable", intensity=7),
MoodTag(name="anxious", intensity=6),
MoodTag(name="ashamed", intensity=4),
],
tags=["work", "poor sleep", "skipped meal"],
)
if __name__ == "__main__":
# Test voice entry
add_entry(
transcript=(
"Feeling pretty scattered today. Work was overwhelming and I "
"snapped at a colleague over something small. Didn't sleep well "
"last night and skipped lunch which always makes things worse."
),
moods=[
MoodTag(name="irritable", intensity=7),
MoodTag(name="anxious", intensity=6),
MoodTag(name="ashamed", intensity=4),
],
tags=["work", "poor sleep", "skipped meal"],
)

View file

11
db.py
View file

@ -1,11 +0,0 @@
import chromadb
def get_collection():
"""
Retrieves chromadb collection by either retrieving one that was already created or by creating a new one
"""
client = chromadb.PersistentClient("./chroma_db")
return client.get_or_create_collection(
name="diary", metadata={"hnsw:space": "cosine"}
)

View file

@ -1,62 +0,0 @@
from openai import OpenAI
from dotenv import load_dotenv
from db import get_collection
if not load_dotenv():
print("⚠️ Warning: .env file not found")
model = "llama3.2"
# create openai client for local model
client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")
# connect and query chromadb
collection = get_collection()
# Use a simple loop for now to discuss with your diary entries
try:
user_question = input(
"Ask a question about your emotional patterns (q to quit): "
).strip()
while True:
# check if user quitting
if user_question.lower() == "q":
break
# ── 1. Retrieve relevant entries from ChromaDB ────────────────────
results = collection.query(query_texts=[user_question], n_results=3)
documents = results["documents"][0]
metadatas = results["metadatas"][0]
# ── 2. Build context string — prompt built AFTER this loop ────────
context = ""
for doc, meta in zip(documents, metadatas):
moods = meta.get("moods", "unknown") or "unknown"
tags = meta.get("tags", "none") or "none"
context += (
f"Date: {meta.get('date', 'unknown')} | Moods: {moods} | Tags: {tags}\n"
)
context += f"Entry: {doc}\n\n"
# ── 3. Build prompt once, after all entries are in context ─────────
prompt = f"""
You are a warm, concise journaling assistant.
Answer in 1-2 sentences maximum.
Always end by asking if the user wants to explore further.
Use only the journal entries below — do not invent details.
Journal entries:
{context}
Question: {user_question}
"""
# ── 4. Send to model and print response ───────────────────────────
response = client.chat.completions.create(
model=model, messages=[{"role": "user", "content": prompt}]
)
print("\n\n" + response.choices[0].message.content)
user_question = input("\nAsk another question (q to quit): ").strip()
finally:
print("Chat ended...")