├── .gitignore ├── .streamlit └── config.toml ├── LICENSE ├── Pipfile ├── Pipfile.lock ├── README.md ├── backend ├── __init__.py └── core.py ├── consts.py ├── ingestion.py ├── main.py └── static └── banner.gif /.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 | langchain-docs/ -------------------------------------------------------------------------------- /.streamlit/config.toml: -------------------------------------------------------------------------------- 1 | [theme] 2 | primaryColor = "#4CAF50" 3 | backgroundColor = "#1E1E1E" 4 | secondaryBackgroundColor = "#252526" 5 | textColor = "#FFFFFF" 6 | font = "sans serif" -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /Pipfile: -------------------------------------------------------------------------------- 1 | [[source]] 2 | url = "https://pypi.org/simple" 3 | verify_ssl = true 4 | name = "pypi" 5 | 6 | [packages] 7 | beautifulsoup4 = "*" 8 | black = "*" 9 | tiktoken = "*" 10 | openai = "*" 11 | unstructured = "*" 12 | nltk = "*" 13 | fastapi = "*" 14 | jinja2 = "*" 15 | uvicorn = "*" 16 | streamlit = "*" 17 | streamlit-chat = "*" 18 | tqdm = "*" 19 | isort = "*" 20 | langchainhub = "*" 21 | firecrawl-py = "*" 22 | langchain-community = "*" 23 | langsmith = "*" 24 | pinecone = "*" 25 | pillow = "*" 26 | 27 | [dev-packages] 28 | 29 | [requires] 30 | python_version = "3.11" 31 | python_full_version = "3.11.0" 32 | 33 | [pipenv] 34 | allow_prereleases = true 35 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 2 | # LangChain Documentation Helper 3 | 4 | A repository for learning LangChain by building a generative ai application. 5 | 6 | This is a web application is using a Pinecone as a vectorsotre and answers questions about LangChain 7 | (sources from LangChain official documentation). 8 | 9 | 10 | 11 | ![Logo](https://github.com/emarco177/documentation-helper/blob/main/static/banner.gif) 12 | [![udemy](https://img.shields.io/badge/LangChain%20Udemy%20Course-%2412.99-green)](https://www.udemy.com/course/langchain/?couponCode=LANGCHAINCD8C0B4060) 13 | 14 | ## Tech Stack 15 | Client: Streamlit 16 | 17 | Server Side: LangChain 🦜🔗 18 | 19 | Vectorstore: Pinecone 🌲 20 | 21 | ## Environment Variables 22 | 23 | To run this project, you will need to add the following environment variables to your .env file 24 | 25 | `PINECONE_API_KEY` 26 | `OPENAI_API_KEY` 27 | 28 | ## Run Locally 29 | 30 | Clone the project 31 | 32 | ```bash 33 | git clone https://github.com/emarco177/documentation-helper.git 34 | ``` 35 | 36 | Go to the project directory 37 | 38 | ```bash 39 | cd documentation-helper 40 | ``` 41 | 42 | Download LangChain Documentation 43 | ```bash 44 | mkdir langchain-docs 45 | wget -r -A.html -P langchain-docs https://api.python.langchain.com/en/latest 46 | ``` 47 | 48 | Install dependencies 49 | 50 | ```bash 51 | pipenv install 52 | ``` 53 | 54 | Start the flask server 55 | 56 | ```bash 57 | streamlit run main.py 58 | ``` 59 | 60 | 61 | ## Running Tests 62 | 63 | To run tests, run the following command 64 | 65 | ```bash 66 | pipenv run pytest . 67 | ``` 68 | 69 | 70 | ## 🔗 Links 71 | [![portfolio](https://img.shields.io/badge/my_portfolio-000?style=for-the-badge&logo=ko-fi&logoColor=white)](https://www.udemy.com/course/langchain/?referralCode=D981B8213164A3EA91AC) 72 | [![linkedin](https://img.shields.io/badge/linkedin-0A66C2?style=for-the-badge&logo=linkedin&logoColor=white)](https://www.linkedin.com/in/eden-marco/) 73 | [![twitter](https://img.shields.io/badge/twitter-1DA1F2?style=for-the-badge&logo=twitter&logoColor=white)](https://www.udemy.com/user/eden-marco/) 74 | -------------------------------------------------------------------------------- /backend/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/emarco177/documentation-helper/aaf8721157907fbd5635fbc9ee8413f9f1d64a98/backend/__init__.py -------------------------------------------------------------------------------- /backend/core.py: -------------------------------------------------------------------------------- 1 | from dotenv import load_dotenv 2 | 3 | load_dotenv() 4 | from langchain_core.output_parsers import StrOutputParser 5 | from langchain_core.runnables import RunnablePassthrough 6 | 7 | 8 | from typing import Any, Dict, List 9 | 10 | from langchain import hub 11 | from langchain.chains.combine_documents import create_stuff_documents_chain 12 | from langchain.chains.history_aware_retriever import create_history_aware_retriever 13 | from langchain.chains.retrieval import create_retrieval_chain 14 | from langchain_openai import ChatOpenAI, OpenAIEmbeddings 15 | from langchain_pinecone import PineconeVectorStore 16 | 17 | from consts import INDEX_NAME 18 | 19 | 20 | def run_llm(query: str, chat_history: List[Dict[str, Any]] = []): 21 | embeddings = OpenAIEmbeddings(model="text-embedding-3-small") 22 | docsearch = PineconeVectorStore(index_name=INDEX_NAME, embedding=embeddings) 23 | chat = ChatOpenAI(verbose=True, temperature=0) 24 | 25 | rephrase_prompt = hub.pull("langchain-ai/chat-langchain-rephrase") 26 | 27 | retrieval_qa_chat_prompt = hub.pull("langchain-ai/retrieval-qa-chat") 28 | stuff_documents_chain = create_stuff_documents_chain(chat, retrieval_qa_chat_prompt) 29 | 30 | history_aware_retriever = create_history_aware_retriever( 31 | llm=chat, retriever=docsearch.as_retriever(), prompt=rephrase_prompt 32 | ) 33 | qa = create_retrieval_chain( 34 | retriever=history_aware_retriever, combine_docs_chain=stuff_documents_chain 35 | ) 36 | 37 | result = qa.invoke(input={"input": query, "chat_history": chat_history}) 38 | return result 39 | 40 | 41 | def format_docs(docs): 42 | return "\n\n".join(doc.page_content for doc in docs) 43 | 44 | 45 | def run_llm2(query: str, chat_history: List[Dict[str, Any]] = []): 46 | embeddings = OpenAIEmbeddings() 47 | docsearch = PineconeVectorStore(index_name=INDEX_NAME, embedding=embeddings) 48 | chat = ChatOpenAI(model_name="gpt-4o", verbose=True, temperature=0) 49 | 50 | rephrase_prompt = hub.pull("langchain-ai/chat-langchain-rephrase") 51 | 52 | retrieval_qa_chat_prompt = hub.pull("langchain-ai/retrieval-qa-chat") 53 | 54 | rag_chain = ( 55 | { 56 | "context": docsearch.as_retriever() | format_docs, 57 | "input": RunnablePassthrough(), 58 | } 59 | | retrieval_qa_chat_prompt 60 | | chat 61 | | StrOutputParser() 62 | ) 63 | 64 | retrieve_docs_chain = (lambda x: x["input"]) | docsearch.as_retriever() 65 | 66 | chain = RunnablePassthrough.assign(context=retrieve_docs_chain).assign( 67 | answer=rag_chain 68 | ) 69 | 70 | result = chain.invoke({"input": query, "chat_history": chat_history}) 71 | return result 72 | -------------------------------------------------------------------------------- /consts.py: -------------------------------------------------------------------------------- 1 | INDEX_NAME = "langchain-doc-index" 2 | -------------------------------------------------------------------------------- /ingestion.py: -------------------------------------------------------------------------------- 1 | import os 2 | 3 | from dotenv import load_dotenv 4 | 5 | load_dotenv() 6 | 7 | from langchain.text_splitter import RecursiveCharacterTextSplitter 8 | from langchain_community.document_loaders import ReadTheDocsLoader 9 | from langchain_openai import OpenAIEmbeddings 10 | from langchain_pinecone import PineconeVectorStore 11 | 12 | from consts import INDEX_NAME 13 | 14 | embeddings = OpenAIEmbeddings(model="text-embedding-3-small") 15 | 16 | 17 | def ingest_docs(): 18 | loader = ReadTheDocsLoader("langchain-docs/api.python.langchain.com/en/latest") 19 | 20 | raw_documents = loader.load() 21 | print(f"loaded {len(raw_documents)} documents") 22 | 23 | text_splitter = RecursiveCharacterTextSplitter(chunk_size=600, chunk_overlap=50) 24 | documents = text_splitter.split_documents(raw_documents) 25 | for doc in documents: 26 | new_url = doc.metadata["source"] 27 | new_url = new_url.replace("langchain-docs", "https:/") 28 | doc.metadata.update({"source": new_url}) 29 | 30 | print(f"Going to add {len(documents)} to Pinecone") 31 | PineconeVectorStore.from_documents(documents, embeddings, index_name=INDEX_NAME) 32 | print("****Loading to vectorstore done ***") 33 | 34 | 35 | def ingest_docs2() -> None: 36 | from langchain_community.document_loaders.firecrawl import FireCrawlLoader 37 | 38 | langchain_documents_base_urls = [ 39 | "https://python.langchain.com/docs/integrations/chat//", 40 | "https://python.langchain.com/docs/integrations/llms/", 41 | "https://python.langchain.com/docs/integrations/text_embedding/", 42 | "https://python.langchain.com/docs/integrations/document_loaders/", 43 | "https://python.langchain.com/docs/integrations/document_transformers/", 44 | "https://python.langchain.com/docs/integrations/vectorstores/", 45 | "https://python.langchain.com/docs/integrations/retrievers/", 46 | "https://python.langchain.com/docs/integrations/tools/", 47 | "https://python.langchain.com/docs/integrations/stores/", 48 | "https://python.langchain.com/docs/integrations/llm_caching/", 49 | "https://python.langchain.com/docs/integrations/graphs/", 50 | "https://python.langchain.com/docs/integrations/memory/", 51 | "https://python.langchain.com/docs/integrations/callbacks/", 52 | "https://python.langchain.com/docs/integrations/chat_loaders/", 53 | "https://python.langchain.com/docs/concepts/", 54 | ] 55 | 56 | langchain_documents_base_urls2 = [ 57 | "https://python.langchain.com/docs/integrations/chat/" 58 | ] 59 | for url in langchain_documents_base_urls2: 60 | print(f"FireCrawling {url=}") 61 | loader = FireCrawlLoader( 62 | url=url, 63 | mode="scrape", 64 | ) 65 | docs = loader.load() 66 | 67 | print(f"Going to add {len(docs)} documents to Pinecone") 68 | PineconeVectorStore.from_documents( 69 | docs, embeddings, index_name="firecrawl-index" 70 | ) 71 | print(f"****Loading {url}* to vectorstore done ***") 72 | 73 | 74 | if __name__ == "__main__": 75 | ingest_docs2() 76 | -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- 1 | from dotenv import load_dotenv 2 | 3 | load_dotenv() 4 | from typing import Set 5 | 6 | import streamlit as st 7 | from streamlit_chat import message 8 | 9 | from backend.core import run_llm 10 | 11 | st.set_page_config( 12 | page_title="Your App Title", 13 | page_icon="🧊", 14 | layout="wide", 15 | initial_sidebar_state="expanded", 16 | ) 17 | # Add these imports 18 | from PIL import Image 19 | import requests 20 | from io import BytesIO 21 | 22 | 23 | def create_sources_string(source_urls: Set[str]) -> str: 24 | if not source_urls: 25 | return "" 26 | sources_list = list(source_urls) 27 | sources_list.sort() 28 | sources_string = "sources:\n" 29 | for i, source in enumerate(sources_list): 30 | sources_string += f"{i+1}. {source}\n" 31 | return sources_string 32 | 33 | 34 | # Add this function to get a profile picture 35 | def get_profile_picture(email): 36 | # This uses Gravatar to get a profile picture based on email 37 | # You can replace this with a different service or use a default image 38 | gravatar_url = f"https://www.gravatar.com/avatar/{hash(email)}?d=identicon&s=200" 39 | response = requests.get(gravatar_url) 40 | img = Image.open(BytesIO(response.content)) 41 | return img 42 | 43 | 44 | # Custom CSS for dark theme and modern look 45 | st.markdown( 46 | """ 47 | 67 | """, 68 | unsafe_allow_html=True, 69 | ) 70 | 71 | # Set page config at the very beginning 72 | 73 | 74 | # Sidebar user information 75 | with st.sidebar: 76 | st.title("User Profile") 77 | 78 | # You can replace these with actual user data 79 | user_name = "John Doe" 80 | user_email = "john.doe@example.com" 81 | 82 | profile_pic = get_profile_picture(user_email) 83 | st.image(profile_pic, width=150) 84 | st.write(f"**Name:** {user_name}") 85 | st.write(f"**Email:** {user_email}") 86 | 87 | st.header("LangChain🦜🔗 Udemy Course- Helper Bot") 88 | 89 | # Initialize session state 90 | if "chat_answers_history" not in st.session_state: 91 | st.session_state["chat_answers_history"] = [] 92 | st.session_state["user_prompt_history"] = [] 93 | st.session_state["chat_history"] = [] 94 | 95 | # Create two columns for a more modern layout 96 | col1, col2 = st.columns([2, 1]) 97 | 98 | with col1: 99 | prompt = st.text_input("Prompt", placeholder="Enter your message here...") 100 | 101 | with col2: 102 | if st.button("Submit", key="submit"): 103 | prompt = prompt or "Hello" # Default message if input is empty 104 | 105 | if prompt: 106 | with st.spinner("Generating response..."): 107 | generated_response = run_llm( 108 | query=prompt, chat_history=st.session_state["chat_history"] 109 | ) 110 | 111 | sources = set(doc.metadata["source"] for doc in generated_response["context"]) 112 | formatted_response = ( 113 | f"{generated_response['answer']} \n\n {create_sources_string(sources)}" 114 | ) 115 | 116 | st.session_state["user_prompt_history"].append(prompt) 117 | st.session_state["chat_answers_history"].append(formatted_response) 118 | st.session_state["chat_history"].append(("human", prompt)) 119 | st.session_state["chat_history"].append(("ai", generated_response["answer"])) 120 | 121 | # Display chat history 122 | if st.session_state["chat_answers_history"]: 123 | for generated_response, user_query in zip( 124 | st.session_state["chat_answers_history"], 125 | st.session_state["user_prompt_history"], 126 | ): 127 | st.chat_message("user").write(user_query) 128 | st.chat_message("assistant").write(generated_response) 129 | 130 | 131 | # Add a footer 132 | st.markdown("---") 133 | st.markdown("Powered by LangChain and Streamlit") 134 | -------------------------------------------------------------------------------- /static/banner.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/emarco177/documentation-helper/aaf8721157907fbd5635fbc9ee8413f9f1d64a98/static/banner.gif --------------------------------------------------------------------------------