├── .devcontainer
    └── devcontainer.json
├── LICENSE
├── Langchain_fastapi.py
├── README.md
├── Screenshot 2024-04-10 100556.png
├── example.pdf
└── requirements.txt


/.devcontainer/devcontainer.json:
--------------------------------------------------------------------------------
 1 | {
 2 |   "name": "Python 3",
 3 |   // Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
 4 |   "image": "mcr.microsoft.com/devcontainers/python:1-3.11-bullseye",
 5 |   "customizations": {
 6 |     "codespaces": {
 7 |       "openFiles": [
 8 |         "README.md",
 9 |         "Langchain_fastapi.py"
10 |       ]
11 |     },
12 |     "vscode": {
13 |       "settings": {},
14 |       "extensions": [
15 |         "ms-python.python",
16 |         "ms-python.vscode-pylance"
17 |       ]
18 |     }
19 |   },
20 |   "updateContentCommand": "[ -f packages.txt ] && sudo apt update && sudo apt upgrade -y && sudo xargs apt install -y <packages.txt; [ -f requirements.txt ] && pip3 install --user -r requirements.txt; pip3 install --user streamlit; echo '✅ Packages installed and Requirements met'",
21 |   "postAttachCommand": {
22 |     "server": "streamlit run Langchain_fastapi.py --server.enableCORS false --server.enableXsrfProtection false"
23 |   },
24 |   "portsAttributes": {
25 |     "8501": {
26 |       "label": "Application",
27 |       "onAutoForward": "openPreview"
28 |     }
29 |   },
30 |   "forwardPorts": [
31 |     8501
32 |   ]
33 | }


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
  1 |                                  Apache License
  2 |                            Version 2.0, January 2004
  3 |                         http://www.apache.org/licenses/
  4 | 
  5 |    TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
  6 | 
  7 |    1. Definitions.
  8 | 
  9 |       "License" shall mean the terms and conditions for use, reproduction,
 10 |       and distribution as defined by Sections 1 through 9 of this document.
 11 | 
 12 |       "Licensor" shall mean the copyright owner or entity authorized by
 13 |       the copyright owner that is granting the License.
 14 | 
 15 |       "Legal Entity" shall mean the union of the acting entity and all
 16 |       other entities that control, are controlled by, or are under common
 17 |       control with that entity. For the purposes of this definition,
 18 |       "control" means (i) the power, direct or indirect, to cause the
 19 |       direction or management of such entity, whether by contract or
 20 |       otherwise, or (ii) ownership of fifty percent (50%) or more of the
 21 |       outstanding shares, or (iii) beneficial ownership of such entity.
 22 | 
 23 |       "You" (or "Your") shall mean an individual or Legal Entity
 24 |       exercising permissions granted by this License.
 25 | 
 26 |       "Source" form shall mean the preferred form for making modifications,
 27 |       including but not limited to software source code, documentation
 28 |       source, and configuration files.
 29 | 
 30 |       "Object" form shall mean any form resulting from mechanical
 31 |       transformation or translation of a Source form, including but
 32 |       not limited to compiled object code, generated documentation,
 33 |       and conversions to other media types.
 34 | 
 35 |       "Work" shall mean the work of authorship, whether in Source or
 36 |       Object form, made available under the License, as indicated by a
 37 |       copyright notice that is included in or attached to the work
 38 |       (an example is provided in the Appendix below).
 39 | 
 40 |       "Derivative Works" shall mean any work, whether in Source or Object
 41 |       form, that is based on (or derived from) the Work and for which the
 42 |       editorial revisions, annotations, elaborations, or other modifications
 43 |       represent, as a whole, an original work of authorship. For the purposes
 44 |       of this License, Derivative Works shall not include works that remain
 45 |       separable from, or merely link (or bind by name) to the interfaces of,
 46 |       the Work and Derivative Works thereof.
 47 | 
 48 |       "Contribution" shall mean any work of authorship, including
 49 |       the original version of the Work and any modifications or additions
 50 |       to that Work or Derivative Works thereof, that is intentionally
 51 |       submitted to Licensor for inclusion in the Work by the copyright owner
 52 |       or by an individual or Legal Entity authorized to submit on behalf of
 53 |       the copyright owner. For the purposes of this definition, "submitted"
 54 |       means any form of electronic, verbal, or written communication sent
 55 |       to the Licensor or its representatives, including but not limited to
 56 |       communication on electronic mailing lists, source code control systems,
 57 |       and issue tracking systems that are managed by, or on behalf of, the
 58 |       Licensor for the purpose of discussing and improving the Work, but
 59 |       excluding communication that is conspicuously marked or otherwise
 60 |       designated in writing by the copyright owner as "Not a Contribution."
 61 | 
 62 |       "Contributor" shall mean Licensor and any individual or Legal Entity
 63 |       on behalf of whom a Contribution has been received by Licensor and
 64 |       subsequently incorporated within the Work.
 65 | 
 66 |    2. Grant of Copyright License. Subject to the terms and conditions of
 67 |       this License, each Contributor hereby grants to You a perpetual,
 68 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 69 |       copyright license to reproduce, prepare Derivative Works of,
 70 |       publicly display, publicly perform, sublicense, and distribute the
 71 |       Work and such Derivative Works in Source or Object form.
 72 | 
 73 |    3. Grant of Patent License. Subject to the terms and conditions of
 74 |       this License, each Contributor hereby grants to You a perpetual,
 75 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 76 |       (except as stated in this section) patent license to make, have made,
 77 |       use, offer to sell, sell, import, and otherwise transfer the Work,
 78 |       where such license applies only to those patent claims licensable
 79 |       by such Contributor that are necessarily infringed by their
 80 |       Contribution(s) alone or by combination of their Contribution(s)
 81 |       with the Work to which such Contribution(s) was submitted. If You
 82 |       institute patent litigation against any entity (including a
 83 |       cross-claim or counterclaim in a lawsuit) alleging that the Work
 84 |       or a Contribution incorporated within the Work constitutes direct
 85 |       or contributory patent infringement, then any patent licenses
 86 |       granted to You under this License for that Work shall terminate
 87 |       as of the date such litigation is filed.
 88 | 
 89 |    4. Redistribution. You may reproduce and distribute copies of the
 90 |       Work or Derivative Works thereof in any medium, with or without
 91 |       modifications, and in Source or Object form, provided that You
 92 |       meet the following conditions:
 93 | 
 94 |       (a) You must give any other recipients of the Work or
 95 |           Derivative Works a copy of this License; and
 96 | 
 97 |       (b) You must cause any modified files to carry prominent notices
 98 |           stating that You changed the files; and
 99 | 
100 |       (c) You must retain, in the Source form of any Derivative Works
101 |           that You distribute, all copyright, patent, trademark, and
102 |           attribution notices from the Source form of the Work,
103 |           excluding those notices that do not pertain to any part of
104 |           the Derivative Works; and
105 | 
106 |       (d) If the Work includes a "NOTICE" text file as part of its
107 |           distribution, then any Derivative Works that You distribute must
108 |           include a readable copy of the attribution notices contained
109 |           within such NOTICE file, excluding those notices that do not
110 |           pertain to any part of the Derivative Works, in at least one
111 |           of the following places: within a NOTICE text file distributed
112 |           as part of the Derivative Works; within the Source form or
113 |           documentation, if provided along with the Derivative Works; or,
114 |           within a display generated by the Derivative Works, if and
115 |           wherever such third-party notices normally appear. The contents
116 |           of the NOTICE file are for informational purposes only and
117 |           do not modify the License. You may add Your own attribution
118 |           notices within Derivative Works that You distribute, alongside
119 |           or as an addendum to the NOTICE text from the Work, provided
120 |           that such additional attribution notices cannot be construed
121 |           as modifying the License.
122 | 
123 |       You may add Your own copyright statement to Your modifications and
124 |       may provide additional or different license terms and conditions
125 |       for use, reproduction, or distribution of Your modifications, or
126 |       for any such Derivative Works as a whole, provided Your use,
127 |       reproduction, and distribution of the Work otherwise complies with
128 |       the conditions stated in this License.
129 | 
130 |    5. Submission of Contributions. Unless You explicitly state otherwise,
131 |       any Contribution intentionally submitted for inclusion in the Work
132 |       by You to the Licensor shall be under the terms and conditions of
133 |       this License, without any additional terms or conditions.
134 |       Notwithstanding the above, nothing herein shall supersede or modify
135 |       the terms of any separate license agreement you may have executed
136 |       with Licensor regarding such Contributions.
137 | 
138 |    6. Trademarks. This License does not grant permission to use the trade
139 |       names, trademarks, service marks, or product names of the Licensor,
140 |       except as required for reasonable and customary use in describing the
141 |       origin of the Work and reproducing the content of the NOTICE file.
142 | 
143 |    7. Disclaimer of Warranty. Unless required by applicable law or
144 |       agreed to in writing, Licensor provides the Work (and each
145 |       Contributor provides its Contributions) on an "AS IS" BASIS,
146 |       WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 |       implied, including, without limitation, any warranties or conditions
148 |       of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 |       PARTICULAR PURPOSE. You are solely responsible for determining the
150 |       appropriateness of using or redistributing the Work and assume any
151 |       risks associated with Your exercise of permissions under this License.
152 | 
153 |    8. Limitation of Liability. In no event and under no legal theory,
154 |       whether in tort (including negligence), contract, or otherwise,
155 |       unless required by applicable law (such as deliberate and grossly
156 |       negligent acts) or agreed to in writing, shall any Contributor be
157 |       liable to You for damages, including any direct, indirect, special,
158 |       incidental, or consequential damages of any character arising as a
159 |       result of this License or out of the use or inability to use the
160 |       Work (including but not limited to damages for loss of goodwill,
161 |       work stoppage, computer failure or malfunction, or any and all
162 |       other commercial damages or losses), even if such Contributor
163 |       has been advised of the possibility of such damages.
164 | 
165 |    9. Accepting Warranty or Additional Liability. While redistributing
166 |       the Work or Derivative Works thereof, You may choose to offer,
167 |       and charge a fee for, acceptance of support, warranty, indemnity,
168 |       or other liability obligations and/or rights consistent with this
169 |       License. However, in accepting such obligations, You may act only
170 |       on Your own behalf and on Your sole responsibility, not on behalf
171 |       of any other Contributor, and only if You agree to indemnify,
172 |       defend, and hold each Contributor harmless for any liability
173 |       incurred by, or claims asserted against, such Contributor by reason
174 |       of your accepting any such warranty or additional liability.
175 | 
176 |    END OF TERMS AND CONDITIONS
177 | 
178 |    APPENDIX: How to apply the Apache License to your work.
179 | 
180 |       To apply the Apache License to your work, attach the following
181 |       boilerplate notice, with the fields enclosed by brackets "[]"
182 |       replaced with your own identifying information. (Don't include
183 |       the brackets!)  The text should be enclosed in the appropriate
184 |       comment syntax for the file format. We also recommend that a
185 |       file or class name and description of purpose be included on the
186 |       same "printed page" as the copyright notice for easier
187 |       identification within third-party archives.
188 | 
189 |    Copyright [yyyy] [name of copyright owner]
190 | 
191 |    Licensed under the Apache License, Version 2.0 (the "License");
192 |    you may not use this file except in compliance with the License.
193 |    You may obtain a copy of the License at
194 | 
195 |        http://www.apache.org/licenses/LICENSE-2.0
196 | 
197 |    Unless required by applicable law or agreed to in writing, software
198 |    distributed under the License is distributed on an "AS IS" BASIS,
199 |    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 |    See the License for the specific language governing permissions and
201 |    limitations under the License.
202 | 


--------------------------------------------------------------------------------
/Langchain_fastapi.py:
--------------------------------------------------------------------------------
  1 | from langchain.chat_models import ChatOpenAI
  2 | from langchain.prompts import ChatPromptTemplate
  3 | from langchain.schema.output_parser import StrOutputParser
  4 | from langchain.schema.runnable import RunnablePassthrough, RunnableLambda
  5 | from langchain_community.utilities import DuckDuckGoSearchAPIWrapper
  6 | from Bio import Entrez
  7 | from datetime import datetime
  8 | from fastapi import FastAPI
  9 | from langserve import add_routes
 10 | import os
 11 | import re
 12 | import streamlit as st
 13 | 
 14 | os.environ["OPENAI_API_KEY"] = st.secrets["OPENAI_API_KEY"]
 15 | 
 16 | 
 17 | 
 18 | Template2 = """
 19 | 
 20 | {text}
 21 | ------------------
 22 | using the text above, answer the following question in short and no more than 500 words.
 23 | Question: {question}
 24 | -------------------------
 25 | if the question can not be answered, dont make up answers and just write that the answer to your question is not withing the document.
 26 | """
 27 | prompt = ChatPromptTemplate.from_template(template=Template2)
 28 | 
 29 | 
 30 | def get_entrez(keywords: list):
 31 |     # Set your email for PubMed requests (required)
 32 |     Entrez.email = "your_email"
 33 | 
 34 |     # Keywords list to search in PubMed
 35 |     keywords_list = keywords
 36 | 
 37 |     # Combine keywords with OR operator for PubMed query. you can also use AND
 38 |     keywords_query = ' AND '.join(keywords_list)
 39 | 
 40 |     # Get today's date in for the text file's name (YYYY/MM/DD)
 41 |     today_date = datetime.today().strftime('%Y-%m-%d')
 42 | 
 43 |     # All you need to search is the keywords query
 44 |     search_query = f'({keywords_query})'
 45 |     search_results = Entrez.read(
 46 |         Entrez.esearch(db="pubmed", term=search_query, retmax=10, datetype="pdat", reldate=30, usehistory="y"))
 47 |     webenv = search_results['WebEnv']
 48 |     query_key = search_results['QueryKey']
 49 |     id_list = search_results['IdList']
 50 |     all_summaries = []
 51 |     # Step 2: EFetch to retrieve titles based on the UIDs
 52 |     for i in id_list:
 53 |         fetch_handle = Entrez.efetch(db="pubmed", id=i, rettype="abstract", retmode="text", webenv=webenv,
 54 |                                      query_key=query_key)
 55 |         fetch_content = fetch_handle.read()
 56 |         all_summaries.append(fetch_content)  # Store title along with summary
 57 |     output = ''.join(all_summaries)
 58 |     return output
 59 | 
 60 | 
 61 | scrape_and_summarize = RunnablePassthrough.assign(
 62 |     text=lambda x: get_entrez(x['keywords'])[:30000]
 63 | ) | prompt | ChatOpenAI(model='gpt-4-1106-preview', temperature=1) | StrOutputParser()
 64 | 
 65 | SEARCH_PROMPT = ChatPromptTemplate.from_messages(
 66 |     [
 67 |         (
 68 |             "user",
 69 |             "Write 3 Pubmed search queries to search online that form an "
 70 |             "objective medical opinion from the following: {question}\n"
 71 |             "You must respond with a list of strings in the following format: "
 72 |             '["query 1", "query 2", "query 3"].',
 73 |         ),
 74 |     ]
 75 | )
 76 | 
 77 | KEY_PROMPT = ChatPromptTemplate.from_messages(
 78 |     [
 79 |         (
 80 |             "user",
 81 |             "Write 3 Pubmed search queries to search online that form an "
 82 |             "objective medical opinion from the following:{question}\n"
 83 |             "then extract important keyword combination from the each question"
 84 |             "You must respond with a list of strings in the following format: "
 85 |             '["keyword_combination 1", "keyword_combination 2", "keyword_combination 3"].',
 86 |         ),
 87 |     ]
 88 | )
 89 | 
 90 | 
 91 | def parse_keywords(output):
 92 |     # Initialize an empty set to store unique keywords
 93 |     unique_keywords = set()
 94 | 
 95 |     # Split the output into lines
 96 |     lines = output['question'].strip().split('\n')
 97 | 
 98 |     # Iterate through each line
 99 |     for line in lines:
100 |         # Extract keywords using regular expression
101 |         keywords = re.findall(r'"([^"]*)"', line)
102 | 
103 |         # Add keywords to the set
104 |         unique_keywords.update(keywords)
105 | 
106 |     # Convert the set to a list and return
107 |     return list(unique_keywords)
108 | 
109 | 
110 | key_search = KEY_PROMPT | ChatOpenAI(model='gpt-4-1106-preview', temperature=1) | {
111 |     'question': StrOutputParser()} | RunnablePassthrough.assign(
112 |     text=lambda x: get_entrez(parse_keywords(x))[:40000]) | prompt |ChatOpenAI(model='gpt-4-1106-preview', temperature=1) | StrOutputParser()
113 | 
114 | 
115 | 
116 | WRITER_SYSTEM_PROMPT = "You are an AI critical thinker research assistant. Your sole purpose is to write well written, critically acclaimed, objective and structured reports on given text."  # noqa: E501
117 | 
118 | RESEARCH_REPORT_TEMPLATE = """Information:
119 | --------
120 | {research_summary}
121 | --------
122 | Using the above information, answer the following question or topic: "{question}" in a detailed report -- \
123 | The report should focus on the answer to the question, should be well structured, informative, \
124 | in depth, with facts and numbers if available and a minimum of 1,200 words.
125 | You should strive to write the report as long as you can using all relevant and necessary information provided.
126 | You must write the report with markdown syntax.
127 | You MUST determine your own concrete and valid opinion based on the given information. Do NOT deter to general and meaningless conclusions.
128 | Write all used source urls at the end of the report, and make sure to not add duplicated sources, but only one reference for each.
129 | You must write the report in apa format.
130 | Please do your best, this is very important to my career."""  # noqa: E501
131 | 
132 | prompt = ChatPromptTemplate.from_messages(
133 |     [
134 |         ("system", WRITER_SYSTEM_PROMPT),
135 |         ("user", RESEARCH_REPORT_TEMPLATE),
136 |     ]
137 | )
138 | 
139 | 
140 | def collapse_list_of_lists(list_of_lists):
141 |     content = []
142 |     for l in list_of_lists:
143 |         content.append("\n\n".join(l))
144 |     return "\n\n".join(content)
145 | 
146 | 
147 | chain = RunnablePassthrough.assign(
148 |     research_summary=key_search | collapse_list_of_lists
149 | ) | prompt | ChatOpenAI(model='gpt-4-1106-preview', temperature=1) | StrOutputParser()
150 | 
151 | system_message = st.text_area("Enter your question")
152 | analyze_button = st.button("Answer")
153 | if analyze_button:
154 |     answer= chain.invoke(
155 |         {
156 |             "question":system_message
157 |         }
158 |     )
159 |     st.write(answer)
160 | 
161 | 
162 | 
163 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # PubMed Question Answering App
 2 | 
 3 | This application allows users to input medical questions and receive answers based on information gathered from PubMed. The answers are generated using the GPT-4 Turbo model, which provides responses in the form of an assay.
 4 | The app utilizes the Streamlit framework for the user interface and requires access to the OpenAI API for model inference.
 5 | 
 6 | ## Installation
 7 | 
 8 | To run the application locally, follow these steps:
 9 | 
10 | - Clone this repository to your local machine.
11 | - Install the required dependencies using pip:
12 | ```bash
13 | pip install -r requirements.txt
14 | ```
15 | - Set up your OpenAI API key by creating a secrets.toml file in the root directory of the project and adding your key:
16 | ```toml
17 | [streamlit]
18 | OPENAI_API_KEY = "your_openai_api_key"
19 | ```
20 | - Run the Streamlit app:
21 | ```bash
22 | streamlit run app.py
23 | 
24 | ```
25 | 
26 | ## Usage
27 | Once the application is running, users can enter their medical questions into the provided text box and click the "Answer" button to receive a response. The app will use the GPT-4 Turbo model to generate answers based on information retrieved from PubMed.
28 | 
29 | ## Example
30 | ![Question and Answer](https://github.com/Soroushsrd/Langchain_app/blob/main/Screenshot%202024-04-10%20100556.png)
31 | 
32 | ## Contributing
33 | 
34 | - This application relies on the LangChain library for natural language processing tasks.
35 | - The GPT-4 Turbo model is provided by OpenAI.
36 | - PubMed is used as a source of medical information.
37 | 
38 | ## License
39 | 
40 | This project is licensed under the [Apache License 2.0](http://www.apache.org/licenses/)
41 | 


--------------------------------------------------------------------------------
/Screenshot 2024-04-10 100556.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Soroushsrd/Langchain_app/3796cb5ef0843c0204b116f979cf6bcf2c200188/Screenshot 2024-04-10 100556.png


--------------------------------------------------------------------------------
/example.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/Soroushsrd/Langchain_app/3796cb5ef0843c0204b116f979cf6bcf2c200188/example.pdf


--------------------------------------------------------------------------------
/requirements.txt:
--------------------------------------------------------------------------------
 1 | altair==5.3.0
 2 | beautifulsoup4==4.12.3
 3 | Bio==1.6.2
 4 | biopython==1.83
 5 | Cython==3.0.10
 6 | docx==0.2.4
 7 | edge_tts==6.1.10
 8 | fake_useragent==1.5.1
 9 | fastapi==0.110.1
10 | googletrans
11 | langchain==0.1.14
12 | langchain_community==0.0.31
13 | langserve==0.0.51
14 | matplotlib==3.8.3
15 | neurokit2==0.2.7
16 | nltk==3.8.1
17 | numpy==1.26.4
18 | ordereddict==1.1
19 | openai
20 | pandas==2.2.1
21 | polars==0.20.18
22 | PyPDF2==3.0.1
23 | pytest==8.1.1
24 | Requests==2.31.0
25 | scipy==1.13.0
26 | seaborn==0.13.2
27 | selenium==4.19.0
28 | setuptools==68.2.2
29 | streamlit==1.32.2
30 | 


--------------------------------------------------------------------------------