├── .gitignore ├── LICENSE ├── README.md ├── app.py └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2024 AI Anytime 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # PubMed-Healthcare-Chatbot 2 | PubMed Healthcare Chatbot. LLM Augmented Q&A over PubMed Search Engine. 3 | 4 | ![Screenshot](https://i.ibb.co/GMbx4Dw/LLM-Augmented-Q-A-over-Pub-Med-Search-Engine.png) 5 | 6 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | from pymed import PubMed 2 | from typing import List 3 | from haystack import component 4 | from haystack import Document 5 | from haystack.components.generators import HuggingFaceTGIGenerator 6 | from dotenv import load_dotenv 7 | import os 8 | from haystack import Pipeline 9 | from haystack.components.builders.prompt_builder import PromptBuilder 10 | import gradio as gr 11 | import time 12 | 13 | load_dotenv() 14 | 15 | os.environ['HUGGINGFACE_API_KEY'] = os.getenv('HUGGINGFACE_API_KEY') 16 | 17 | 18 | pubmed = PubMed(tool="Haystack2.0Prototype", email="dummyemail@gmail.com") 19 | 20 | def documentize(article): 21 | return Document(content=article.abstract, meta={'title': article.title, 'keywords': article.keywords}) 22 | 23 | @component 24 | class PubMedFetcher(): 25 | 26 | @component.output_types(articles=List[Document]) 27 | def run(self, queries: list[str]): 28 | cleaned_queries = queries[0].strip().split('\n') 29 | 30 | articles = [] 31 | try: 32 | for query in cleaned_queries: 33 | response = pubmed.query(query, max_results = 1) 34 | documents = [documentize(article) for article in response] 35 | articles.extend(documents) 36 | except Exception as e: 37 | print(e) 38 | print(f"Couldn't fetch articles for queries: {queries}" ) 39 | results = {'articles': articles} 40 | return results 41 | 42 | keyword_llm = HuggingFaceTGIGenerator("mistralai/Mixtral-8x7B-Instruct-v0.1") 43 | keyword_llm.warm_up() 44 | 45 | llm = HuggingFaceTGIGenerator("mistralai/Mixtral-8x7B-Instruct-v0.1") 46 | llm.warm_up() 47 | 48 | 49 | keyword_prompt_template = """ 50 | Your task is to convert the following question into 3 keywords that can be used to find relevant medical research papers on PubMed. 51 | Here is an examples: 52 | question: "What are the latest treatments for major depressive disorder?" 53 | keywords: 54 | Antidepressive Agents 55 | Depressive Disorder, Major 56 | Treatment-Resistant depression 57 | --- 58 | question: {{ question }} 59 | keywords: 60 | """ 61 | 62 | prompt_template = """ 63 | Answer the question truthfully based on the given documents. 64 | If the documents don't contain an answer, use your existing knowledge base. 65 | 66 | q: {{ question }} 67 | Articles: 68 | {% for article in articles %} 69 | {{article.content}} 70 | keywords: {{article.meta['keywords']}} 71 | title: {{article.meta['title']}} 72 | {% endfor %} 73 | 74 | """ 75 | 76 | keyword_prompt_builder = PromptBuilder(template=keyword_prompt_template) 77 | 78 | prompt_builder = PromptBuilder(template=prompt_template) 79 | fetcher = PubMedFetcher() 80 | 81 | pipe = Pipeline() 82 | 83 | pipe.add_component("keyword_prompt_builder", keyword_prompt_builder) 84 | pipe.add_component("keyword_llm", keyword_llm) 85 | pipe.add_component("pubmed_fetcher", fetcher) 86 | pipe.add_component("prompt_builder", prompt_builder) 87 | pipe.add_component("llm", llm) 88 | 89 | pipe.connect("keyword_prompt_builder.prompt", "keyword_llm.prompt") 90 | pipe.connect("keyword_llm.replies", "pubmed_fetcher.queries") 91 | 92 | pipe.connect("pubmed_fetcher.articles", "prompt_builder.articles") 93 | pipe.connect("prompt_builder.prompt", "llm.prompt") 94 | 95 | def ask(question): 96 | output = pipe.run(data={"keyword_prompt_builder":{"question":question}, 97 | "prompt_builder":{"question": question}, 98 | "llm":{"generation_kwargs": {"max_new_tokens": 500}}}) 99 | print(question) 100 | print(output['llm']['replies'][0]) 101 | return output['llm']['replies'][0] 102 | 103 | # result = ask("How are mRNA vaccines being used for cancer treatment?") 104 | 105 | # print(result) 106 | 107 | iface = gr.Interface(fn=ask, inputs=gr.Textbox( 108 | value="How are mRNA vaccines being used for cancer treatment?"), 109 | outputs="markdown", 110 | title="LLM Augmented Q&A over PubMed Search Engine", 111 | description="Ask a question about BioMedical and get an answer from a friendly AI assistant.", 112 | examples=[["How are mRNA vaccines being used for cancer treatment?"], 113 | ["Suggest me some Case Studies related to Pneumonia."], 114 | ["Tell me about HIV AIDS."],["Suggest some case studies related to Auto Immune Disorders."], 115 | ["How to treat a COVID infected Patient?"]], 116 | theme=gr.themes.Soft(), 117 | allow_flagging="never",) 118 | 119 | iface.launch(debug=True) 120 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | haystack-ai 2 | pymed 3 | gradio 4 | python-dotenv 5 | transformers --------------------------------------------------------------------------------