mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-04 04:28:58 +00:00
PubMed document loader (#8893)
- added `PubMed Document Loader` artifacts; ut-s; examples - fixed `PubMed utility`; ut-s @hwchase17
This commit is contained in:
Leonid Ganeline
GitHub
139
docs/extras/integrations/document_loaders/pubmed.ipynb
Normal file
139
docs/extras/integrations/document_loaders/pubmed.ipynb
Normal file
@@ -0,0 +1,139 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3df0dcf8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# PubMed\n",
|
||||
"\n",
|
||||
">[PubMed®](https://pubmed.ncbi.nlm.nih.gov/) by `The National Center for Biotechnology Information, National Library of Medicine` comprises more than 35 million citations for biomedical literature from `MEDLINE`, life science journals, and online books. Citations may include links to full text content from `PubMed Central` and publisher web sites."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "aecaff63",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.document_loaders import PubMedLoader"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "f2f7e8d3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = PubMedLoader(\"chatgpt\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "ed115aa1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"docs = loader.load()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "b68d3264-b893-45e4-8ab0-077b25a586dc",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"3"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"len(docs)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "9f4626d2-068d-4aed-9ffe-ad754ad4b4cd",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'uid': '37548997',\n",
|
||||
" 'Title': 'Performance of ChatGPT on the Situational Judgement Test-A Professional Dilemmas-Based Examination for Doctors in the United Kingdom.',\n",
|
||||
" 'Published': '2023-08-07',\n",
|
||||
" 'Copyright Information': '©Robin J Borchert, Charlotte R Hickman, Jack Pepys, Timothy J Sadler. Originally published in JMIR Medical Education (https://mededu.jmir.org), 07.08.2023.'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"docs[1].metadata"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "8000f687-b500-4cce-841b-70d6151304da",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"BACKGROUND: ChatGPT is a large language model that has performed well on professional examinations in the fields of medicine, law, and business. However, it is unclear how ChatGPT would perform on an examination assessing professionalism and situational judgement for doctors.\\nOBJECTIVE: We evaluated the performance of ChatGPT on the Situational Judgement Test (SJT): a national examination taken by all final-year medical students in the United Kingdom. This examination is designed to assess attributes such as communication, teamwork, patient safety, prioritization skills, professionalism, and ethics.\\nMETHODS: All questions from the UK Foundation Programme Office's (UKFPO's) 2023 SJT practice examination were inputted into ChatGPT. For each question, ChatGPT's answers and rationales were recorded and assessed on the basis of the official UK Foundation Programme Office scoring template. Questions were categorized into domains of Good Medical Practice on the basis of the domains referenced in the rationales provided in the scoring sheet. Questions without clear domain links were screened by reviewers and assigned one or multiple domains. ChatGPT's overall performance, as well as its performance across the domains of Good Medical Practice, was evaluated.\\nRESULTS: Overall, ChatGPT performed well, scoring 76% on the SJT but scoring full marks on only a few questions (9%), which may reflect possible flaws in ChatGPT's situational judgement or inconsistencies in the reasoning across questions (or both) in the examination itself. ChatGPT demonstrated consistent performance across the 4 outlined domains in Good Medical Practice for doctors.\\nCONCLUSIONS: Further research is needed to understand the potential applications of large language models, such as ChatGPT, in medical education for standardizing questions and providing consistent rationales for examinations assessing professionalism and ethics.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"docs[1].page_content"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1070e571-697d-4c33-9a4f-0b2dd6909629",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
30
docs/extras/integrations/providers/pubmed.md
Normal file
30
docs/extras/integrations/providers/pubmed.md
Normal file
@@ -0,0 +1,30 @@
|
||||
# PubMed
|
||||
|
||||
# PubMed
|
||||
|
||||
>[PubMed®](https://pubmed.ncbi.nlm.nih.gov/) by `The National Center for Biotechnology Information, National Library of Medicine`
|
||||
> comprises more than 35 million citations for biomedical literature from `MEDLINE`, life science journals, and online books.
|
||||
> Citations may include links to full text content from `PubMed Central` and publisher web sites.
|
||||
|
||||
## Setup
|
||||
You need to install a python package.
|
||||
|
||||
```bash
|
||||
pip install xmltodict
|
||||
```
|
||||
|
||||
### Retriever
|
||||
|
||||
See a [usage example](/docs/integrations/retrievers/pubmed).
|
||||
|
||||
```python
|
||||
from langchain.retrievers import PubMedRetriever
|
||||
```
|
||||
|
||||
### Document Loader
|
||||
|
||||
See a [usage example](/docs/integrations/document_loaders/pubmed).
|
||||
|
||||
```python
|
||||
from langchain.document_loaders import PubMedLoader
|
||||
```
|
||||
@@ -7,14 +7,15 @@
|
||||
"source": [
|
||||
"# PubMed\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use `PubMed` as a retriever\n",
|
||||
"\n",
|
||||
"`PubMed®` comprises more than 35 million citations for biomedical literature from `MEDLINE`, life science journals, and online books. Citations may include links to full text content from `PubMed Central` and publisher web sites."
|
||||
">[PubMed®](https://pubmed.ncbi.nlm.nih.gov/) by `The National Center for Biotechnology Information, National Library of Medicine` comprises more than 35 million citations for biomedical literature from `MEDLINE`, life science journals, and online books. Citations may include links to full text content from `PubMed Central` and publisher web sites.\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use `PubMed` as a retriever"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 12,
|
||||
"id": "aecaff63",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -24,7 +25,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 34,
|
||||
"id": "f2f7e8d3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -34,19 +35,19 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"execution_count": 35,
|
||||
"id": "ed115aa1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='', metadata={'uid': '37268021', 'title': 'Dermatology in the wake of an AI revolution: who gets a say?', 'pub_date': '<Year>2023</Year><Month>May</Month><Day>31</Day>'}),\n",
|
||||
" Document(page_content='', metadata={'uid': '37267643', 'title': 'What is ChatGPT and what do we do with it? Implications of the age of AI for nursing and midwifery practice and education: An editorial.', 'pub_date': '<Year>2023</Year><Month>May</Month><Day>30</Day>'}),\n",
|
||||
" Document(page_content='The nursing field has undergone notable changes over time and is projected to undergo further modifications in the future, owing to the advent of sophisticated technologies and growing healthcare needs. The advent of ChatGPT, an AI-powered language model, is expected to exert a significant influence on the nursing profession, specifically in the domains of patient care and instruction. The present article delves into the ramifications of ChatGPT within the nursing domain and accentuates its capacity and constraints to transform the discipline.', metadata={'uid': '37266721', 'title': 'The Impact of ChatGPT on the Nursing Profession: Revolutionizing Patient Care and Education.', 'pub_date': '<Year>2023</Year><Month>Jun</Month><Day>02</Day>'})]"
|
||||
"[Document(page_content='', metadata={'uid': '37549050', 'Title': 'ChatGPT: \"To Be or Not to Be\" in Bikini Bottom.', 'Published': '--', 'Copyright Information': ''}),\n",
|
||||
" Document(page_content=\"BACKGROUND: ChatGPT is a large language model that has performed well on professional examinations in the fields of medicine, law, and business. However, it is unclear how ChatGPT would perform on an examination assessing professionalism and situational judgement for doctors.\\nOBJECTIVE: We evaluated the performance of ChatGPT on the Situational Judgement Test (SJT): a national examination taken by all final-year medical students in the United Kingdom. This examination is designed to assess attributes such as communication, teamwork, patient safety, prioritization skills, professionalism, and ethics.\\nMETHODS: All questions from the UK Foundation Programme Office's (UKFPO's) 2023 SJT practice examination were inputted into ChatGPT. For each question, ChatGPT's answers and rationales were recorded and assessed on the basis of the official UK Foundation Programme Office scoring template. Questions were categorized into domains of Good Medical Practice on the basis of the domains referenced in the rationales provided in the scoring sheet. Questions without clear domain links were screened by reviewers and assigned one or multiple domains. ChatGPT's overall performance, as well as its performance across the domains of Good Medical Practice, was evaluated.\\nRESULTS: Overall, ChatGPT performed well, scoring 76% on the SJT but scoring full marks on only a few questions (9%), which may reflect possible flaws in ChatGPT's situational judgement or inconsistencies in the reasoning across questions (or both) in the examination itself. ChatGPT demonstrated consistent performance across the 4 outlined domains in Good Medical Practice for doctors.\\nCONCLUSIONS: Further research is needed to understand the potential applications of large language models, such as ChatGPT, in medical education for standardizing questions and providing consistent rationales for examinations assessing professionalism and ethics.\", metadata={'uid': '37548997', 'Title': 'Performance of ChatGPT on the Situational Judgement Test-A Professional Dilemmas-Based Examination for Doctors in the United Kingdom.', 'Published': '2023-08-07', 'Copyright Information': '©Robin J Borchert, Charlotte R Hickman, Jack Pepys, Timothy J Sadler. Originally published in JMIR Medical Education (https://mededu.jmir.org), 07.08.2023.'}),\n",
|
||||
" Document(page_content='', metadata={'uid': '37548971', 'Title': \"Large Language Models Answer Medical Questions Accurately, but Can't Match Clinicians' Knowledge.\", 'Published': '2023-08-07', 'Copyright Information': ''})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"execution_count": 35,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -54,6 +55,14 @@
|
||||
"source": [
|
||||
"retriever.get_relevant_documents(\"chatgpt\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a9ff7a25-bb4b-4cd5-896d-72f70f4af49b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@@ -72,7 +81,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.6"
|
||||
"version": "3.10.12"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
Reference in New Issue
Block a user