Add component pubmed (#1586)

### What problem does this PR solve?

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

graph/component/__init__.py

@@ -12,6 +12,7 @@ from .keyword import KeywordExtract, KeywordExtractParam
 from .baidu import Baidu, BaiduParam
 from .duckduckgo import DuckDuckGo, DuckDuckGoParam
 from .wikipedia import Wikipedia, WikipediaParam
+from .pubmed import PubMed, PubMedParam
 
 
 def component_class(class_name):

graph/component/pubmed.py

@@ -0,0 +1,63 @@
+#
+#  Copyright 2024 The InfiniFlow Authors. All Rights Reserved.
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+import random
+from abc import ABC
+from functools import partial
+from Bio import Entrez
+import pandas as pd
+import xml.etree.ElementTree as ET
+from graph.settings import DEBUG
+from graph.component.base import ComponentBase, ComponentParamBase
+
+
+class PubMedParam(ComponentParamBase):
+    """
+    Define the PubMed component parameters.
+    """
+
+    def __init__(self):
+        super().__init__()
+        self.top_n = 5
+        self.email = "A.N.Other@example.com"
+
+    def check(self):
+        self.check_positive_integer(self.top_n, "Top N")
+
+
+class PubMed(ComponentBase, ABC):
+    component_name = "PubMed"
+
+    def _run(self, history, **kwargs):
+        ans = self.get_input()
+        ans = " - ".join(ans["content"]) if "content" in ans else ""
+        if not ans:
+            return PubMed.be_output("")
+
+        Entrez.email = self._param.email
+        pubmedids = Entrez.read(Entrez.esearch(db='pubmed', retmax=self._param.top_n, term=ans))['IdList']
+        pubmedcnt = ET.fromstring(
+            Entrez.efetch(db='pubmed', id=",".join(pubmedids), retmode="xml").read().decode("utf-8"))
+        pubmed_res = [{"content": 'Title:' + child.find("MedlineCitation").find("Article").find(
+            "ArticleTitle").text + '\nUrl:<a href=" https://pubmed.ncbi.nlm.nih.gov/' + child.find(
+            "MedlineCitation").find("PMID").text + '">' + '</a>\n' + 'Abstract:' + child.find("MedlineCitation").find(
+            "Article").find("Abstract").find("AbstractText").text} for child in pubmedcnt.findall("PubmedArticle")]
+
+        if not pubmed_res:
+            return PubMed.be_output("")
+
+        df = pd.DataFrame(pubmed_res)
+        if DEBUG: print(df, ":::::::::::::::::::::::::::::::::")
+        return df

requirements.txt

@@ -1,5 +1,6 @@
 Aspose.Slides==24.2.0
 BCEmbedding==0.1.3
+Bio==1.7.1
 boto3==1.34.140
 botocore==1.34.140
 cachetools==5.3.3

requirements_arm.txt

@@ -151,3 +151,4 @@ duckduckgo_search==6.1.9
 google-generativeai==0.7.2
 groq==0.9.0
 wikipedia==1.4.0
+Bio==1.7.1

requirements_dev.txt

@@ -136,3 +136,4 @@ duckduckgo_search==6.1.9
 google-generativeai==0.7.2
 groq==0.9.0
 wikipedia==1.4.0
+Bio==1.7.1