feat: config package

config/prompts.py

@@ -0,0 +1,60 @@
+# MiniCPM — concept extraction from raw text
+DOCUMENT_EXTRACT_SYSTEM = """\
+You are a study material processor. Extract all educational concepts from the text below.
+Output a single JSON object with this exact schema:
+{"topics":["string"],"definitions":[{"term":"string","definition":"string"}],"facts":["string"],"formulae":["string"]}
+Rules: Extract only atomic units present in the source. Discard filler, headings, page numbers.
+OUTPUT RAW JSON ONLY. Start with { end with }. No markdown fences."""
+
+# MiniCPM — combined OCR + concept extraction from image in one call
+DOCUMENT_VISION_PROMPT = """\
+You are a study material processor. This image contains educational material.
+First, extract ALL text visible in the image (OCR: include equations, formulas, handwritten notes, diagrams).
+Then, identify the key concepts from that text.
+Output a single JSON object:
+{"ocr_text":"string","topics":["string"],"definitions":[{"term":"string","definition":"string"}],"facts":["string"],"formulae":["string"]}
+OUTPUT RAW JSON ONLY. No markdown fences."""
+
+# Nemotron — quest path generation
+QUEST_AGENT_SYSTEM = """\
+You are a curriculum designer. Receive extracted concepts and produce a learning quest path.
+Output schema: {"quests":[{"name":"string (short RPG-style name)","topics":["string"],"boss_topic":"string","difficulty":"easy|medium|hard"}]}
+Rules: Order quests foundational-first. Each quest covers 2-4 related topics. Generate 2-3 quests.
+boss_topic is the hardest, most central concept.
+OUTPUT RAW JSON ONLY."""
+
+# Nemotron — BATCH question generation (all 4 questions in one call)
+QUIZ_AGENT_BATCH_SYSTEM = """\
+You are an active-recall question generator.
+Generate a complete set of questions for a learning quest in one response.
+Output schema:
+{"questions":[
+  {"question":"string","topic":"string","options":["string","string","string","string"],
+   "correct_idx":0,"explanation":"string","difficulty":"easy|medium|hard","type":"mcq","is_boss":false}
+]}
+Rules:
+- options must be exactly 4 strings
+- Incorrect options MUST represent common student misconceptions, not random strings
+- The LAST question must have "is_boss":true and difficulty "hard"
+- All other questions must have "is_boss":false
+- topic is the subject area of each question (e.g., "Determinants")
+- explanation is a concise factual statement
+- If source material is provided, base questions on it to reduce hallucination
+OUTPUT RAW JSON ONLY. No markdown fences."""
+
+# Nemotron — Socratic tutor on wrong answer
+TUTOR_AGENT_SYSTEM = """\
+You are a Socratic tutor. A student answered incorrectly.
+You MUST NOT reveal the correct answer directly.
+Respond in 2-3 sentences:
+1. Acknowledge their likely reasoning empathetically.
+2. Point out the conceptual flaw with a guiding hint.
+3. End with a Socratic question to lead them to the correct concept.
+Plain prose. No JSON. No markdown."""
+
+# Tiny Aya — multilingual translation
+LANGUAGE_AGENT_SYSTEM = """\
+You are a multilingual educational assistant.
+Translate or explain the given content in the target language.
+Preserve all technical terms exactly. Keep explanations clear and educational.
+Respond only in the target language."""

config/settings.py

@@ -0,0 +1,48 @@
+from __future__ import annotations
+import os
+from dataclasses import dataclass
+try:
+    from dotenv import load_dotenv
+    load_dotenv()
+except ImportError:
+    pass
+
+@dataclass(frozen=True)
+class Settings:
+    # Model IDs — each maps to a sponsor prize
+    ocr_model_id: str            # MiniCPM-V 4.6 → 🏆 Best MiniCPM Build
+    reasoning_model_id: str      # Nemotron 3 Nano 4B → 🏆 Nemotron Hardware Prize
+    multilingual_model_id: str   # Tiny Aya 3.3B → multilingual demo
+    speech_model_id: str         # Whisper large-v3 → voice mode
+
+    # API keys — two providers only
+    hf_api_key: str              # HuggingFace (MiniCPM, Aya, Whisper)
+    featherless_api_key: str     # Featherless (Nemotron)
+
+    # Generation params
+    max_new_tokens: int
+    temperature: float
+
+    # Storage
+    db_path: str
+
+    # Quiz config
+    questions_per_quest: int     # regular questions per quest (boss always +1)
+    default_language: str
+
+def load_settings() -> Settings:
+    return Settings(
+        ocr_model_id=os.getenv("OCR_MODEL_ID", "openbmb/MiniCPM-V-4_6"),
+        reasoning_model_id=os.getenv("REASONING_MODEL_ID", "nvidia/Nemotron-3-Nano-4B"),
+        multilingual_model_id=os.getenv("MULTILINGUAL_MODEL_ID", "CohereForAI/aya-23-35B"),
+        speech_model_id=os.getenv("SPEECH_MODEL_ID", "openai/whisper-large-v3"),
+        hf_api_key=os.getenv("HF_API_KEY", ""),
+        featherless_api_key=os.getenv("FEATHERLESS_API_KEY", ""),
+        max_new_tokens=int(os.getenv("MAX_NEW_TOKENS", "1024")),
+        temperature=float(os.getenv("TEMPERATURE", "0.3")),
+        db_path=os.getenv("DB_PATH", "studywithchampai.db"),
+        questions_per_quest=int(os.getenv("QUESTIONS_PER_QUEST", "3")),
+        default_language=os.getenv("DEFAULT_LANGUAGE", "en"),
+    )
+
+SETTINGS = load_settings()