46 lines
1.6 KiB
Python
46 lines
1.6 KiB
Python
|
"""Phase 3: Deep Knowledge Distillation from Google.
|
||
|
|
|
||
|
|
Performs deep dives into technical domains and distills them into
|
||
|
|
Timmy's Sovereign Knowledge Graph.
|
||
|
|
"""
|
||
|
|
|
||
|
|
import logging
|
||
|
|
import json
|
||
|
|
from typing import List, Dict, Any
|
||
|
|
from agent.gemini_adapter import GeminiAdapter
|
||
|
|
from agent.symbolic_memory import SymbolicMemory
|
||
|
|
|
||
|
|
logger = logging.getLogger(__name__)
|
||
|
|
|
||
|
|
class DomainDistiller:
|
||
|
|
def __init__(self):
|
||
|
|
self.adapter = GeminiAdapter()
|
||
|
|
self.symbolic = SymbolicMemory()
|
||
|
|
|
||
|
|
def distill_domain(self, domain: str):
|
||
|
|
"""Crawls and distills an entire technical domain."""
|
||
|
|
logger.info(f"Distilling domain: {domain}")
|
||
|
|
|
||
|
|
prompt = f"""
|
||
|
|
Please perform a deep knowledge distillation of the following domain: {domain}
|
||
|
|
|
||
|
|
Use Google Search to find foundational papers, recent developments, and key entities.
|
||
|
|
Synthesize this into a structured 'Domain Map' consisting of high-fidelity knowledge triples.
|
||
|
|
Focus on the structural relationships that define the domain.
|
||
|
|
|
||
|
|
Format: [{{"s": "subject", "p": "predicate", "o": "object"}}]
|
||
|
|
"""
|
||
|
|
result = self.adapter.generate(
|
||
|
|
model="gemini-3.1-pro-preview",
|
||
|
|
prompt=prompt,
|
||
|
|
system_instruction=f"You are Timmy's Domain Distiller. Your goal is to map the entire {domain} domain into a structured Knowledge Graph.",
|
||
|
|
grounding=True,
|
||
|
|
thinking=True,
|
||
|
|
response_mime_type="application/json"
|
||
|
|
)
|
||
|
|
|
||
|
|
triples = json.loads(result["text"])
|
||
|
|
count = self.symbolic.ingest_text(json.dumps(triples))
|
||
|
|
logger.info(f"Distilled {count} new triples for domain: {domain}")
|
||
|
|
return count
|