File size: 8,068 Bytes
78fefe8 af492db e5aa007 af492db 78fefe8 b286843 78fefe8 a3443f4 78fefe8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 |
from typing import Dict, Tuple
import google.generativeai as genai
import json
import faiss
from openai import OpenAI
import numpy as np
import os
import pandas as pd
genai.configure(
api_key=os.environ.get("gemini-2.5-flash")
)
model = genai.GenerativeModel("gemini-2.5-pro")
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
csv_path = os.path.join(BASE_DIR, "..", "data", "CATHODES_DATASET.csv")
csv_path = os.path.abspath(csv_path)
# Load cathode dataset once (adjust path if needed)
df_base = pd.read_csv(csv_path)
def query_faiss_index(query_text,
faiss_index_path=None,
metadata_path=None,
top_k=5):
openai_api_key = os.getenv("OPENAI_API_KEY")
if not openai_api_key:
raise ValueError("OPENAI_API_KEY is not set")
client = OpenAI(api_key=openai_api_key)
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
if faiss_index_path is None:
faiss_index_path = os.path.join(BASE_DIR, "../sentiment/faiss_index.idx")
if metadata_path is None:
metadata_path = os.path.join(BASE_DIR, "../sentiment/metadata.json")
# Load index and metadata
index = faiss.read_index(faiss_index_path)
with open(metadata_path, "r", encoding="utf-8") as f:
metadata = json.load(f)
# Get embedding for query
response = client.embeddings.create(
input=query_text.lower(),
model="text-embedding-3-large"
)
query_embedding = response.data[0].embedding
query_embedding_np = np.array([query_embedding]).astype("float32")
faiss.normalize_L2(query_embedding_np)
# Search index
distances, indices = index.search(query_embedding_np, top_k)
results = []
for dist, idx in zip(distances[0], indices[0]):
meta = metadata[idx]
results.append({
"score": float(dist),
"source_pdf": meta["source_pdf"],
"page": meta["page"],
"chunk_index": meta["chunk_index"],
"text_snippet": meta["text"]
})
return results
def calculate_np_ratio(
Q_anode_raw: float,
m_anode: float,
SEI_loss_fraction: float,
Q_cathode_raw: float,
m_cathode: float,
vacancy_loss_fraction: float
) -> float:
"""
N/P = (Q_anode_raw * m_anode * (1 - SEI_loss)) /
(Q_cathode_raw * m_cathode * (1 - vacancy_loss))
"""
Q_anode_usable = Q_anode_raw * m_anode * (1 - SEI_loss_fraction)
Q_cathode_usable = Q_cathode_raw * m_cathode * (1 - vacancy_loss_fraction)
return Q_anode_usable / Q_cathode_usable
def recommended_mass_loading_areal(
Q_areal: float,
Q_anode: float,
Q_cathode: float,
NP_ratio: float
) -> Tuple[float, float]:
"""
Returns (m_cathode_mg_cm2, m_anode_mg_cm2)
"""
m_cathode = Q_areal / Q_cathode
m_anode = (Q_areal / Q_anode) * NP_ratio
# convert g/cm² → mg/cm²
return m_cathode * 1000, m_anode * 1000
def calculate_first_cycle_ce(
Q_charge_anode: float,
Q_discharge_anode: float,
Q_charge_cathode: float,
Q_discharge_cathode: float,
Q_charge_full: float,
Q_discharge_full: float
) -> Dict[str, float]:
ce_anode = (Q_discharge_anode / Q_charge_anode) * 100
ce_cathode= (Q_discharge_cathode / Q_charge_cathode) * 100
ce_full = (Q_discharge_full / Q_charge_full) * 100
return {
"CE_anode (%)": ce_anode,
"CE_cathode (%)": ce_cathode,
"CE_full_cell (%)": ce_full
}
def estimate_irreversible_na_loss(
Q_charge_full: float,
Q_discharge_full: float
) -> float:
"""
Irreversible Na⁺ loss per gram (mAh/g) on first cycle
"""
return Q_charge_full - Q_discharge_full
def generate_gemini_insight(input_data: Dict, results: Dict, faiss_results: list, cathode_name: str) -> str:
prompt = f"""Remove the underscores and .pdf from the source_pdf field in the RAG section below and put it as References at the end of the explanation.
You are to explain the results of the calculations of a sodium-ion full cell battery using hard carbon and {cathode_name}. You are a RAG system that takes information only from the RAG section below.
Respond with an EXTENSIVE/LONG EXPLANATIONS, scientific, and straight-to-the-point explanation without any additional opinions, explaining only the results of the calculations.
Lastly, briefly analyze the performance of the full cell battery.
### Input Data:
{json.dumps(input_data, indent=2)}
### Calculated Results:
{json.dumps(results, indent=2)}
### Formulas Used:
- N/P Ratio = (Q_anode_raw × m_anode × (1 − SEI_loss_fraction)) ÷ (Q_cathode_raw × m_cathode × (1 − vacancy_loss_fraction))\n"
- Mass Loading Areal (mg/cm²):\n"
- m_cathode = Q_areal ÷ Q_cathode
- m_anode = (Q_areal ÷ Q_anode) × N/P Ratio
- First Cycle Coulombic Efficiency (CE):
- CE_anode = (Q_discharge_anode ÷ Q_charge_anode) × 100
- CE_cathode = (Q_discharge_cathode ÷ Q_charge_cathode) × 100
- CE_full = (Q_discharge_full ÷ Q_charge_full) × 100
- Irreversible Na⁺ Loss = Q_charge_full − Q_discharge_full
Remove the underscores and .pdf from the source_pdf field in the RAG section below and put it as References at the end of the explanation.
Do not include the PDF file name directly in the explanation.
At the end of the explanation, list the full source_pdf file names used as references.
RAG Section, use only the information from this section to explain the results:
{json.dumps(faiss_results, indent=2)}
"""
try:
response = model.generate_content(prompt)
if response.candidates:
parts = response.candidates[0].content.parts
text_output = " ".join(
p.text for p in parts if hasattr(p, "text") and p.text
)
return text_output.strip()
else:
return "Gemini returned no candidates."
except Exception as e:
return f"Gemini Error: {str(e)}"
def calculate_all_d(cathode_name: str, input_data: Dict) -> Dict:
# 1) N/P ratio
np_ratio = calculate_np_ratio(
Q_anode_raw = input_data["Q_anode_raw"],
m_anode = input_data["m_anode"],
SEI_loss_fraction = input_data["SEI_loss_fraction"],
Q_cathode_raw = input_data["Q_cathode_raw"],
m_cathode = input_data["m_cathode"],
vacancy_loss_fraction = input_data["vacancy_loss_fraction"]
)
# 2) Recommended mass loading
m_cathode_mg_cm2, m_anode_mg_cm2 = recommended_mass_loading_areal(
Q_areal = input_data["Q_areal"],
Q_anode = input_data["Q_anode_raw"],
Q_cathode = input_data["Q_cathode_raw"],
NP_ratio = np_ratio
)
# 3) First‑cycle CE
ce = calculate_first_cycle_ce(
Q_charge_anode = input_data["Q_charge_anode"],
Q_discharge_anode = input_data["Q_discharge_anode"],
Q_charge_cathode = input_data["Q_charge_cathode"],
Q_discharge_cathode = input_data["Q_discharge_cathode"],
Q_charge_full = input_data["Q_charge_full"],
Q_discharge_full = input_data["Q_discharge_full"]
)
# 4) Irreversible Na⁺ loss
ir_loss = estimate_irreversible_na_loss(
Q_charge_full = input_data["Q_charge_full"],
Q_discharge_full = input_data["Q_discharge_full"]
)
results = {
"NP_ratio": np_ratio,
"m_cathode_mg_per_cm2": m_cathode_mg_cm2,
"m_anode_mg_per_cm2": m_anode_mg_cm2,
**ce,
"Irreversible_Na_loss (mAh/g)": ir_loss
}
query_text = (
f"Sodium-ion battery with hard carbon anode and cathode {cathode_name}. "
)
faiss_results = query_faiss_index(query_text, top_k=5)
# 5) Generate Gemini insight
gemini_summary = generate_gemini_insight(input_data, results, faiss_results, cathode_name)
return {
"results": results,
"Gemini_Explanation": gemini_summary
}
|