Spaces:
Sleeping
Sleeping
Delete module
Browse files- module/module_2_tool_executor.py +0 -135
module/module_2_tool_executor.py
DELETED
|
@@ -1,135 +0,0 @@
|
|
| 1 |
-
# ==========================================================
|
| 2 |
-
# PATHOGENAGENT - MODULE 2: TOOL EXECUTOR
|
| 3 |
-
# ==========================================================
|
| 4 |
-
|
| 5 |
-
import requests
|
| 6 |
-
import time
|
| 7 |
-
from typing import List, Dict
|
| 8 |
-
|
| 9 |
-
class ToolExecutor:
|
| 10 |
-
"""اجرای ابزارها و بازیابی شواهد از NCBI"""
|
| 11 |
-
|
| 12 |
-
def __init__(self):
|
| 13 |
-
self.headers = {"User-Agent": "PathogenAgent/1.0"}
|
| 14 |
-
self.last_request_time = 0
|
| 15 |
-
|
| 16 |
-
def _wait_for_rate_limit(self):
|
| 17 |
-
"""Rate Limiting (حداکثر ۳ درخواست در ثانیه)"""
|
| 18 |
-
current_time = time.time()
|
| 19 |
-
if current_time - self.last_request_time < 0.333:
|
| 20 |
-
time.sleep(0.333 - (current_time - self.last_request_time))
|
| 21 |
-
self.last_request_time = time.time()
|
| 22 |
-
|
| 23 |
-
def execute(self, query: str, tools: List[str]) -> Dict:
|
| 24 |
-
"""اجرای ابزارهای درخواستی"""
|
| 25 |
-
results = {}
|
| 26 |
-
|
| 27 |
-
if "PubMed" in tools:
|
| 28 |
-
results["PubMed"] = self._search_pubmed(query)
|
| 29 |
-
|
| 30 |
-
if "ClinVar" in tools:
|
| 31 |
-
results["ClinVar"] = self._search_clinvar(query)
|
| 32 |
-
|
| 33 |
-
if "GenBank" in tools:
|
| 34 |
-
results["GenBank"] = self._search_genbank(query)
|
| 35 |
-
|
| 36 |
-
return results
|
| 37 |
-
|
| 38 |
-
def _search_pubmed(self, query: str) -> List[Dict]:
|
| 39 |
-
"""جستجوی PubMed"""
|
| 40 |
-
try:
|
| 41 |
-
self._wait_for_rate_limit()
|
| 42 |
-
|
| 43 |
-
# ESearch
|
| 44 |
-
url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
|
| 45 |
-
params = {"db": "pubmed", "term": query, "retmax": 3, "retmode": "json"}
|
| 46 |
-
resp = requests.get(url, params=params, headers=self.headers, timeout=10)
|
| 47 |
-
ids = resp.json().get("esearchresult", {}).get("idlist", [])
|
| 48 |
-
|
| 49 |
-
if not ids:
|
| 50 |
-
return []
|
| 51 |
-
|
| 52 |
-
# ESummary
|
| 53 |
-
self._wait_for_rate_limit()
|
| 54 |
-
url2 = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi"
|
| 55 |
-
params2 = {"db": "pubmed", "id": ",".join(ids), "retmode": "json"}
|
| 56 |
-
resp2 = requests.get(url2, params=params2, headers=self.headers, timeout=10)
|
| 57 |
-
data = resp2.json()
|
| 58 |
-
|
| 59 |
-
results = []
|
| 60 |
-
for uid, rec in data.get("result", {}).items():
|
| 61 |
-
if uid == "uids":
|
| 62 |
-
continue
|
| 63 |
-
title = rec.get("title", "")
|
| 64 |
-
if title:
|
| 65 |
-
results.append({
|
| 66 |
-
"title": title,
|
| 67 |
-
"source": "PubMed",
|
| 68 |
-
"identifier": f"PMID:{uid}"
|
| 69 |
-
})
|
| 70 |
-
|
| 71 |
-
return results
|
| 72 |
-
|
| 73 |
-
except Exception as e:
|
| 74 |
-
print(f"⚠️ PubMed Error: {e}")
|
| 75 |
-
return []
|
| 76 |
-
|
| 77 |
-
def _search_clinvar(self, query: str) -> List[Dict]:
|
| 78 |
-
"""جستجوی ClinVar"""
|
| 79 |
-
try:
|
| 80 |
-
self._wait_for_rate_limit()
|
| 81 |
-
|
| 82 |
-
url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
|
| 83 |
-
params = {"db": "clinvar", "term": query, "retmax": 3, "retmode": "json"}
|
| 84 |
-
resp = requests.get(url, params=params, headers=self.headers, timeout=10)
|
| 85 |
-
ids = resp.json().get("esearchresult", {}).get("idlist", [])
|
| 86 |
-
|
| 87 |
-
if not ids:
|
| 88 |
-
return []
|
| 89 |
-
|
| 90 |
-
self._wait_for_rate_limit()
|
| 91 |
-
url2 = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi"
|
| 92 |
-
params2 = {"db": "clinvar", "id": ",".join(ids), "retmode": "json"}
|
| 93 |
-
resp2 = requests.get(url2, params=params2, headers=self.headers, timeout=10)
|
| 94 |
-
data = resp2.json()
|
| 95 |
-
|
| 96 |
-
results = []
|
| 97 |
-
for uid, rec in data.get("result", {}).items():
|
| 98 |
-
if uid == "uids":
|
| 99 |
-
continue
|
| 100 |
-
title = rec.get("title", "")
|
| 101 |
-
if title:
|
| 102 |
-
results.append({
|
| 103 |
-
"title": title,
|
| 104 |
-
"source": "ClinVar",
|
| 105 |
-
"identifier": f"RCV:{uid}"
|
| 106 |
-
})
|
| 107 |
-
|
| 108 |
-
return results
|
| 109 |
-
|
| 110 |
-
except Exception as e:
|
| 111 |
-
print(f"⚠️ ClinVar Error: {e}")
|
| 112 |
-
return []
|
| 113 |
-
|
| 114 |
-
def _search_genbank(self, query: str) -> List[Dict]:
|
| 115 |
-
"""جستجوی GenBank"""
|
| 116 |
-
try:
|
| 117 |
-
self._wait_for_rate_limit()
|
| 118 |
-
|
| 119 |
-
url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
|
| 120 |
-
params = {"db": "nucleotide", "term": f"{query}[Organism]", "retmax": 1, "retmode": "json"}
|
| 121 |
-
resp = requests.get(url, params=params, headers=self.headers, timeout=10)
|
| 122 |
-
ids = resp.json().get("esearchresult", {}).get("idlist", [])
|
| 123 |
-
|
| 124 |
-
if not ids:
|
| 125 |
-
return []
|
| 126 |
-
|
| 127 |
-
return [{
|
| 128 |
-
"title": f"{query} genome",
|
| 129 |
-
"source": "GenBank",
|
| 130 |
-
"identifier": f"GenBank:{ids[0]}"
|
| 131 |
-
}]
|
| 132 |
-
|
| 133 |
-
except Exception as e:
|
| 134 |
-
print(f"⚠️ GenBank Error: {e}")
|
| 135 |
-
return []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|