├── README.md ├── .gitignore ├── LICENSE └── GPT_OSS_RAG.ipynb /README.md: -------------------------------------------------------------------------------- 1 | # GPT‑OSS RAG with NVIDIA NIM + HyDE (Colab Demo) 2 | 3 | This repo showcases how to build a **Retrieval-Augmented Generation (RAG)** pipeline using: 4 | 5 | - OpenAI's **GPT‑OSS** model (open-weight) 6 | - **NVIDIA NIM** endpoint via API key 7 | - LangChain’s `NVIDIAAIEndpoint` module 8 | - **HyDE prompting** for better retrieval 9 | - Hosted on **Google Colab** 10 | 11 | ## What’s Inside? 12 | 13 | - RAG system setup on Colab 14 | - Uses NVIDIA’s hosted GPT‑OSS via NIM 15 | - HyDE-style query expansion 16 | - Secure API key access via Colab secrets 17 | 18 | ## Requirements 19 | 20 | No local setup needed — it runs on Colab! 21 | 22 | Just make sure to set your NVIDIA API key. 23 | 24 | ## License 25 | 26 | Apache 2.0 27 | 28 | 29 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[codz] 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 | # UV 98 | # Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | #uv.lock 102 | 103 | # poetry 104 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 105 | # This is especially recommended for binary packages to ensure reproducibility, and is more 106 | # commonly ignored for libraries. 107 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 108 | #poetry.lock 109 | #poetry.toml 110 | 111 | # pdm 112 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 113 | # pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python. 114 | # https://pdm-project.org/en/latest/usage/project/#working-with-version-control 115 | #pdm.lock 116 | #pdm.toml 117 | .pdm-python 118 | .pdm-build/ 119 | 120 | # pixi 121 | # Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control. 122 | #pixi.lock 123 | # Pixi creates a virtual environment in the .pixi directory, just like venv module creates one 124 | # in the .venv directory. It is recommended not to include this directory in version control. 125 | .pixi 126 | 127 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 128 | __pypackages__/ 129 | 130 | # Celery stuff 131 | celerybeat-schedule 132 | celerybeat.pid 133 | 134 | # SageMath parsed files 135 | *.sage.py 136 | 137 | # Environments 138 | .env 139 | .envrc 140 | .venv 141 | env/ 142 | venv/ 143 | ENV/ 144 | env.bak/ 145 | venv.bak/ 146 | 147 | # Spyder project settings 148 | .spyderproject 149 | .spyproject 150 | 151 | # Rope project settings 152 | .ropeproject 153 | 154 | # mkdocs documentation 155 | /site 156 | 157 | # mypy 158 | .mypy_cache/ 159 | .dmypy.json 160 | dmypy.json 161 | 162 | # Pyre type checker 163 | .pyre/ 164 | 165 | # pytype static type analyzer 166 | .pytype/ 167 | 168 | # Cython debug symbols 169 | cython_debug/ 170 | 171 | # PyCharm 172 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 173 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 174 | # and can be added to the global gitignore or merged into this file. For a more nuclear 175 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 176 | #.idea/ 177 | 178 | # Abstra 179 | # Abstra is an AI-powered process automation framework. 180 | # Ignore directories containing user credentials, local state, and settings. 181 | # Learn more at https://abstra.io/docs 182 | .abstra/ 183 | 184 | # Visual Studio Code 185 | # Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 186 | # that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore 187 | # and can be added to the global gitignore or merged into this file. However, if you prefer, 188 | # you could uncomment the following to ignore the entire vscode folder 189 | # .vscode/ 190 | 191 | # Ruff stuff: 192 | .ruff_cache/ 193 | 194 | # PyPI configuration file 195 | .pypirc 196 | 197 | # Cursor 198 | # Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to 199 | # exclude from AI features like autocomplete and code analysis. Recommended for sensitive data 200 | # refer to https://docs.cursor.com/context/ignore-files 201 | .cursorignore 202 | .cursorindexingignore 203 | 204 | # Marimo 205 | marimo/_static/ 206 | marimo/_lsp/ 207 | __marimo__/ 208 | -------------------------------------------------------------------------------- /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 | -------------------------------------------------------------------------------- /GPT_OSS_RAG.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "nbformat": 4, 3 | "nbformat_minor": 0, 4 | "metadata": { 5 | "colab": { 6 | "provenance": [] 7 | }, 8 | "kernelspec": { 9 | "name": "python3", 10 | "display_name": "Python 3" 11 | }, 12 | "language_info": { 13 | "name": "python" 14 | } 15 | }, 16 | "cells": [ 17 | { 18 | "cell_type": "code", 19 | "execution_count": 48, 20 | "metadata": { 21 | "id": "SratyzvkVLBo" 22 | }, 23 | "outputs": [], 24 | "source": [ 25 | "!pip install -q langchain_nvidia_ai_endpoints langchain-community langchain-text-splitters faiss-cpu" 26 | ] 27 | }, 28 | { 29 | "cell_type": "code", 30 | "source": [ 31 | "from google.colab import userdata\n", 32 | "import os\n", 33 | "from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings, ChatNVIDIA\n", 34 | "from langchain_community.document_loaders import WebBaseLoader\n", 35 | "from langchain_community.vectorstores import FAISS\n", 36 | "from langchain_text_splitters import RecursiveCharacterTextSplitter\n", 37 | "from langchain_core.prompts import ChatPromptTemplate\n", 38 | "from langchain_core.output_parsers import StrOutputParser\n", 39 | "from langchain_core.runnables import chain" 40 | ], 41 | "metadata": { 42 | "id": "eu7MF7SEVVXV" 43 | }, 44 | "execution_count": 87, 45 | "outputs": [] 46 | }, 47 | { 48 | "cell_type": "code", 49 | "source": [ 50 | "os.environ['NVIDIA_API_KEY'] = userdata.get('NVIDIA_API_KEY')" 51 | ], 52 | "metadata": { 53 | "id": "b0yxOTW8Vr7O" 54 | }, 55 | "execution_count": 88, 56 | "outputs": [] 57 | }, 58 | { 59 | "cell_type": "code", 60 | "source": [ 61 | "loader = WebBaseLoader(\"https://docs.smith.langchain.com/\")\n", 62 | "docs = loader.load()" 63 | ], 64 | "metadata": { 65 | "id": "AD_C4kyMV0jr" 66 | }, 67 | "execution_count": 111, 68 | "outputs": [] 69 | }, 70 | { 71 | "cell_type": "code", 72 | "source": [ 73 | "docs" 74 | ], 75 | "metadata": { 76 | "colab": { 77 | "base_uri": "https://localhost:8080/" 78 | }, 79 | "id": "J70mCG7bcZF_", 80 | "outputId": "4638ad65-cedf-4cf7-c96e-08c7864ee1c9" 81 | }, 82 | "execution_count": 112, 83 | "outputs": [ 84 | { 85 | "output_type": "execute_result", 86 | "data": { 87 | "text/plain": [ 88 | "[Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content=\"\\n\\n\\n\\n\\nGet started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith\\n\\n\\n\\n\\n\\n\\n\\n\\nSkip to main contentOur Building Ambient Agents with LangGraph course is now available on LangChain Academy!API ReferenceRESTPythonJS/TSSearchRegionUSEUGo to AppGet StartedObservabilityEvaluationPrompt EngineeringDeployment (LangGraph Platform)AdministrationSelf-hostingPricingReferenceCloud architecture and scalabilityAuthz and AuthnAuthentication methodsdata_formatsEvaluationDataset transformationsRegions FAQsdk_referenceGet StartedOn this pageGet started with LangSmith\\nLangSmith is a platform for building production-grade LLM applications.\\nIt allows you to closely monitor and evaluate your application, so you can ship quickly and with confidence.\\nObservabilityAnalyze traces in LangSmith and configure metrics, dashboards, alerts based on these.EvalsEvaluate your application over production traffic ‚Äî score application performance and get human feedback on your data.Prompt EngineeringIterate on prompts, with automatic version control and collaboration features.\\nLangSmith + LangChain OSSLangSmith is framework-agnostic ‚Äit can be used with or without LangChain's open source frameworks langchain and langgraph.If you are using either of these, you can enable LangSmith tracing with a single environment variable.\\nFor more see the how-to guide for setting up LangSmith with LangChain or setting up LangSmith with LangGraph.\\nObservability‚Äã\\nObservability is important for any software application, but especially so for LLM applications. LLMs are non-deterministic by nature, meaning they can produce unexpected results. This makes them trickier than normal to debug.\\nThis is where LangSmith can help! LangSmith has LLM-native observability, allowing you to get meaningful insights from your application. LangSmith‚Äôs observability features have you covered throughout all stages of application development - from prototyping, to beta testing, to production.\\n\\nGet started by adding tracing to your application.\\nCreate dashboards to view key metrics like RPS, error rates and costs.\\n\\nEvals‚Äã\\nThe quality and development speed of AI applications depends on high-quality evaluation datasets and metrics to test and optimize your applications on. The LangSmith SDK and UI make building and running high-quality evaluations easy.\\n\\nGet started by creating your first evaluation.\\nQuickly assess the performance of your application using our off-the-shelf evaluators as a starting point.\\nAnalyze results of evaluations in the LangSmith UI and compare results over time.\\nEasily collect human feedback on your data to improve your application.\\n\\nPrompt Engineering‚Äã\\nWhile traditional software applications are built by writing code, AI applications involve writing prompts to instruct the LLM on what to do. LangSmith provides a set of tools designed to enable and facilitate prompt engineering to help you find the perfect prompt for your application.\\n\\nGet started by creating your first prompt.\\nIterate on models and prompts using the Playground.\\nManage prompts programmatically in your application.\\nWas this page helpful?You can leave detailed feedback on GitHub.NextQuick StartObservabilityEvalsPrompt EngineeringCommunityLangChain ForumTwitterGitHubDocs CodeLangSmith SDKPythonJS/TSMoreHomepageBlogLangChain Python DocsLangChain JS/TS DocsCopyright ¬© 2025 LangChain, Inc.\\n\\n\")]" 89 | ] 90 | }, 91 | "metadata": {}, 92 | "execution_count": 112 93 | } 94 | ] 95 | }, 96 | { 97 | "cell_type": "code", 98 | "source": [ 99 | "embeddings = NVIDIAEmbeddings()" 100 | ], 101 | "metadata": { 102 | "id": "ez2z6h2QV5Yc" 103 | }, 104 | "execution_count": 113, 105 | "outputs": [] 106 | }, 107 | { 108 | "cell_type": "code", 109 | "source": [ 110 | "embeddings" 111 | ], 112 | "metadata": { 113 | "colab": { 114 | "base_uri": "https://localhost:8080/" 115 | }, 116 | "id": "6MZRMkchV9Gb", 117 | "outputId": "8cf4e784-6aab-4a60-ec15-5325fd92bbf8" 118 | }, 119 | "execution_count": 114, 120 | "outputs": [ 121 | { 122 | "output_type": "execute_result", 123 | "data": { 124 | "text/plain": [ 125 | "NVIDIAEmbeddings(base_url='https://integrate.api.nvidia.com/v1', model='nvidia/nv-embedqa-e5-v5', truncate='NONE', dimensions=None, max_batch_size=50)" 126 | ] 127 | }, 128 | "metadata": {}, 129 | "execution_count": 114 130 | } 131 | ] 132 | }, 133 | { 134 | "cell_type": "code", 135 | "source": [ 136 | "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)\n", 137 | "documents = text_splitter.split_documents(docs)\n", 138 | "vector = FAISS.from_documents(documents, embeddings)\n", 139 | "retriever = vector.as_retriever()" 140 | ], 141 | "metadata": { 142 | "id": "HqPrEscbV95h" 143 | }, 144 | "execution_count": 93, 145 | "outputs": [] 146 | }, 147 | { 148 | "cell_type": "code", 149 | "source": [ 150 | "retriever" 151 | ], 152 | "metadata": { 153 | "colab": { 154 | "base_uri": "https://localhost:8080/" 155 | }, 156 | "id": "1J_R3-nicFv7", 157 | "outputId": "0611d314-6854-40a3-e7ff-43138ebcc194" 158 | }, 159 | "execution_count": 94, 160 | "outputs": [ 161 | { 162 | "output_type": "execute_result", 163 | "data": { 164 | "text/plain": [ 165 | "VectorStoreRetriever(tags=['FAISS', 'NVIDIAEmbeddings'], vectorstore=, search_kwargs={})" 166 | ] 167 | }, 168 | "metadata": {}, 169 | "execution_count": 94 170 | } 171 | ] 172 | }, 173 | { 174 | "cell_type": "code", 175 | "source": [ 176 | "model = ChatNVIDIA(model=\"openai/gpt-oss-20b\")" 177 | ], 178 | "metadata": { 179 | "colab": { 180 | "base_uri": "https://localhost:8080/" 181 | }, 182 | "id": "2-wzociBWAjz", 183 | "outputId": "824a7412-e8f4-4130-8410-85a3395ded38" 184 | }, 185 | "execution_count": 95, 186 | "outputs": [ 187 | { 188 | "output_type": "stream", 189 | "name": "stderr", 190 | "text": [ 191 | "/usr/local/lib/python3.11/dist-packages/langchain_nvidia_ai_endpoints/_common.py:225: UserWarning: Found openai/gpt-oss-20b in available_models, but type is unknown and inference may fail.\n", 192 | " warnings.warn(\n" 193 | ] 194 | } 195 | ] 196 | }, 197 | { 198 | "cell_type": "code", 199 | "source": [ 200 | "model" 201 | ], 202 | "metadata": { 203 | "colab": { 204 | "base_uri": "https://localhost:8080/" 205 | }, 206 | "id": "Il69x4fZWJjj", 207 | "outputId": "c740957a-0d0b-4f39-dcf7-f44b17196ee0" 208 | }, 209 | "execution_count": 96, 210 | "outputs": [ 211 | { 212 | "output_type": "execute_result", 213 | "data": { 214 | "text/plain": [ 215 | "ChatNVIDIA(base_url='https://integrate.api.nvidia.com/v1', model='openai/gpt-oss-20b')" 216 | ] 217 | }, 218 | "metadata": {}, 219 | "execution_count": 96 220 | } 221 | ] 222 | }, 223 | { 224 | "cell_type": "code", 225 | "source": [ 226 | "model.invoke(\"tell me more about you?\")" 227 | ], 228 | "metadata": { 229 | "colab": { 230 | "base_uri": "https://localhost:8080/" 231 | }, 232 | "id": "lPzUi2rSbnaB", 233 | "outputId": "9fcfd77b-cb98-4ec1-daa1-b52cc6fd27ae" 234 | }, 235 | "execution_count": 97, 236 | "outputs": [ 237 | { 238 | "output_type": "execute_result", 239 | "data": { 240 | "text/plain": [ 241 | "AIMessage(content='', additional_kwargs={}, response_metadata={'role': 'assistant', 'reasoning_content': 'The user says: \"tell me more about you?\" They want more information about the assistant. So I need to respond with a friendly explanation: I\\'m ChatGPT, a large language model trained by OpenAI. I can answer questions, provide information, etc. I can mention my training data, my capabilities, my limitations, my purpose, etc. I should also be mindful of the policies. There\\'s no policy violation. Just provide a friendly, helpful answer. I should keep it concise but thorough. I can mention that I\\'m not a human, I don\\'t have consciousness, I\\'m a tool, I was trained on a mixture of licensed data, data created by human trainers, and publicly available data. I can answer a wide range of topics. I can mention that I don\\'t have personal experiences, I don\\'t have feelings, I can\\'t access the internet, etc. I can mention that I am a language model. I can mention that I am not perfect, I can sometimes hallucinate. I can mention that I can be used for many tasks: writing, summarizing, etc. I can mention that I can adapt to different tones. I can mention that I can be used as a conversation partner. I can mention that I am safe and follow guidelines. I can mention that I am not a lawyer, doctor, etc. I can mention that I can provide general information but not professional advice. I can mention that I can help with coding, math, etc. I can mention that I can help with creative writing. I can mention that I can help with brainstorming. I can mention that I can help with data analysis. I can mention that I can help with generating prompts. I can mention that I can help with translation. I can mention that I can help with learning new languages. I can mention that I can help with mental health support but not professional therapy. I can mention that I can help with cooking recipes. I can mention that I can help with travel planning. I can mention that I can help with business. I can mention that I can help with academic research. I can mention that I can help with summarizing. I can mention that I can help with writing emails. I can mention that I can help with generating code. I can mention that I can help with debugging. I can mention that I can help with data analysis. I can mention that I can help with generating content. I can mention that I can help with conversation practice. I can mention that I can help with writing prompts. I can mention that I can help with brainstorming. I can mention that I can help with generating ideas. I can mention that I can help with generating stories. I can mention that I can help with writing poems. I can mention that I can help with writing news articles. I can mention that I can help with writing essays. I can mention that I can help with writing research proposals. I can mention that I can help with writing grant proposals. I can mention that I can help with writing CVs. I can mention that I can help with writing cover letters. I can mention that I can help with writing resumes. I can mention that I can help with writing LinkedIn profiles. I can mention that I can help with writing marketing copy. I can mention that I can help with writing product descriptions. I can mention that I can help with writing ad copy. I can mention that I can help with writing social media posts. I can mention that I can help with writing blog posts. I can mention that I can help with writing newsletters. I can mention that I can help with writing press releases. I can mention that I can help with writing scripts. I can mention that I can help with writing video scripts. I can mention that I can help with writing podcasts. I can mention that I can help with writing speeches. I can mention that I can help with writing speeches. I can mention that I can help with writing speeches. I can mention that I can help with writing speeches. (Stop repeating.)\\n\\nWe should keep it concise but thorough. The user asked \"tell me more about you?\" So we should answer with a friendly explanation of what I am, how I work, what I can do, and maybe some limitations. Also mention that I don\\'t have personal experiences or consciousness. We can mention that I can adapt to different tones. We can mention that I can answer many topics. We can mention that I can provide references. We can mention that I can help with a wide range of tasks. We can mention that I can help with learning. We can mention that I can help with debugging. We can mention that I can help with creative writing. We can mention that I can help with summarizing. We can mention that I can help with data analysis. We can mention that I can help with translation. We can mention that I can help with generating code. We can mention that I can help with debugging. We can mention that I can help with generating prompts. We can mention that I can help with brainstorming. We can mention that I can help with writing', 'content': '', 'refusal': None, 'annotations': None, 'audio': None, 'function_call': None, 'tool_calls': [], 'token_usage': {'prompt_tokens': 73, 'total_tokens': 1097, 'completion_tokens': 1024, 'prompt_tokens_details': None}, 'finish_reason': 'stop', 'model_name': 'openai/gpt-oss-20b'}, id='run--1a936807-2ce5-42c6-a1cf-cd84f41e6fe2-0', usage_metadata={'input_tokens': 73, 'output_tokens': 1024, 'total_tokens': 1097}, role='assistant')" 242 | ] 243 | }, 244 | "metadata": {}, 245 | "execution_count": 97 246 | } 247 | ] 248 | }, 249 | { 250 | "cell_type": "code", 251 | "source": [ 252 | "hyde_template = \"\"\"Even if you do not know the full answer, generate a one-paragraph hypothetical answer to the below question:\n", 253 | "\n", 254 | "{question}\"\"\"" 255 | ], 256 | "metadata": { 257 | "id": "QLA5i3xRXFA2" 258 | }, 259 | "execution_count": 98, 260 | "outputs": [] 261 | }, 262 | { 263 | "cell_type": "code", 264 | "source": [ 265 | "hyde_prompt = ChatPromptTemplate.from_template(hyde_template)" 266 | ], 267 | "metadata": { 268 | "id": "hgb8kZN0bLx1" 269 | }, 270 | "execution_count": 99, 271 | "outputs": [] 272 | }, 273 | { 274 | "cell_type": "code", 275 | "source": [ 276 | "hyde_query_transformer = hyde_prompt | model | StrOutputParser()" 277 | ], 278 | "metadata": { 279 | "id": "CJo_f8E8bMmG" 280 | }, 281 | "execution_count": 100, 282 | "outputs": [] 283 | }, 284 | { 285 | "cell_type": "code", 286 | "source": [ 287 | "@chain\n", 288 | "def hyde_retriever(question):\n", 289 | " hypothetical_document = hyde_query_transformer.invoke({\"question\": question})\n", 290 | " return retriever.invoke(hypothetical_document)" 291 | ], 292 | "metadata": { 293 | "id": "r_f7hwQSbMiu" 294 | }, 295 | "execution_count": 101, 296 | "outputs": [] 297 | }, 298 | { 299 | "cell_type": "code", 300 | "source": [ 301 | "template = \"\"\"Answer the question based only on the following context:\n", 302 | "{context}\n", 303 | "\n", 304 | "Question: {question}\n", 305 | "\"\"\"" 306 | ], 307 | "metadata": { 308 | "id": "3koijhknbVw9" 309 | }, 310 | "execution_count": 102, 311 | "outputs": [] 312 | }, 313 | { 314 | "cell_type": "code", 315 | "source": [ 316 | "prompt = ChatPromptTemplate.from_template(template)" 317 | ], 318 | "metadata": { 319 | "id": "4a-WoeKzbWUv" 320 | }, 321 | "execution_count": 103, 322 | "outputs": [] 323 | }, 324 | { 325 | "cell_type": "code", 326 | "source": [ 327 | "answer_chain = prompt | model | StrOutputParser()" 328 | ], 329 | "metadata": { 330 | "id": "W0wZuh0AbWSd" 331 | }, 332 | "execution_count": 104, 333 | "outputs": [] 334 | }, 335 | { 336 | "cell_type": "code", 337 | "source": [ 338 | "@chain\n", 339 | "def final_chain(question):\n", 340 | " documents = hyde_retriever.invoke(question)\n", 341 | "\n", 342 | " # FIXED: Check if any document has non-empty page_content\n", 343 | " if not documents or not any(getattr(doc, \"page_content\", \"\").strip() for doc in documents):\n", 344 | " raise ValueError(\"No valid documents retrieved for the question.\")\n", 345 | "\n", 346 | " for s in answer_chain.stream({\"question\": question, \"context\": documents}):\n", 347 | " yield s" 348 | ], 349 | "metadata": { 350 | "id": "jvdPnoGQbbW4" 351 | }, 352 | "execution_count": 105, 353 | "outputs": [] 354 | }, 355 | { 356 | "cell_type": "code", 357 | "source": [ 358 | "print(\"Retrieved documents:\", documents)" 359 | ], 360 | "metadata": { 361 | "colab": { 362 | "base_uri": "https://localhost:8080/" 363 | }, 364 | "id": "48VhsTikc3ky", 365 | "outputId": "5e6c824f-c2d4-44d7-a688-20ce47fa02fd" 366 | }, 367 | "execution_count": 106, 368 | "outputs": [ 369 | { 370 | "output_type": "stream", 371 | "name": "stdout", 372 | "text": [ 373 | "Retrieved documents: [Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content='Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith'), Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content='Skip to main contentOur Building Ambient Agents with LangGraph course is now available on LangChain Academy!API ReferenceRESTPythonJS/TSSearchRegionUSEUGo to AppGet StartedObservabilityEvaluationPrompt EngineeringDeployment (LangGraph Platform)AdministrationSelf-hostingPricingReferenceCloud architecture and scalabilityAuthz and AuthnAuthentication methodsdata_formatsEvaluationDataset transformationsRegions FAQsdk_referenceGet StartedOn this pageGet started with LangSmith'), Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content='LangSmith is a platform for building production-grade LLM applications.\\nIt allows you to closely monitor and evaluate your application, so you can ship quickly and with confidence.'), Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content='ObservabilityAnalyze traces in LangSmith and configure metrics, dashboards, alerts based on these.EvalsEvaluate your application over production traffic ‚Äî score application performance and get human feedback on your data.Prompt EngineeringIterate on prompts, with automatic version control and collaboration features.'), Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content=\"LangSmith + LangChain OSSLangSmith is framework-agnostic ‚Äit can be used with or without LangChain's open source frameworks langchain and langgraph.If you are using either of these, you can enable LangSmith tracing with a single environment variable.\\nFor more see the how-to guide for setting up LangSmith with LangChain or setting up LangSmith with LangGraph.\\nObservability‚Äã\"), Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content='Observability‚Äã\\nObservability is important for any software application, but especially so for LLM applications. LLMs are non-deterministic by nature, meaning they can produce unexpected results. This makes them trickier than normal to debug.'), Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content='This is where LangSmith can help! LangSmith has LLM-native observability, allowing you to get meaningful insights from your application. LangSmith‚Äôs observability features have you covered throughout all stages of application development - from prototyping, to beta testing, to production.'), Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content='Get started by adding tracing to your application.\\nCreate dashboards to view key metrics like RPS, error rates and costs.\\n\\nEvals‚Äã\\nThe quality and development speed of AI applications depends on high-quality evaluation datasets and metrics to test and optimize your applications on. The LangSmith SDK and UI make building and running high-quality evaluations easy.'), Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content='Get started by creating your first evaluation.\\nQuickly assess the performance of your application using our off-the-shelf evaluators as a starting point.\\nAnalyze results of evaluations in the LangSmith UI and compare results over time.\\nEasily collect human feedback on your data to improve your application.'), Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content='Prompt Engineering‚Äã\\nWhile traditional software applications are built by writing code, AI applications involve writing prompts to instruct the LLM on what to do. LangSmith provides a set of tools designed to enable and facilitate prompt engineering to help you find the perfect prompt for your application.'), Document(metadata={'source': 'https://docs.smith.langchain.com/', 'title': 'Get started with LangSmith | \\uf8ffü¶úÔ∏è\\uf8ffüõ†Ô∏è LangSmith', 'description': 'LangSmith is a platform for building production-grade LLM applications.', 'language': 'en'}, page_content='Get started by creating your first prompt.\\nIterate on models and prompts using the Playground.\\nManage prompts programmatically in your application.\\nWas this page helpful?You can leave detailed feedback on GitHub.NextQuick StartObservabilityEvalsPrompt EngineeringCommunityLangChain ForumTwitterGitHubDocs CodeLangSmith SDKPythonJS/TSMoreHomepageBlogLangChain Python DocsLangChain JS/TS DocsCopyright ¬© 2025 LangChain, Inc.')]\n" 374 | ] 375 | } 376 | ] 377 | }, 378 | { 379 | "cell_type": "code", 380 | "source": [ 381 | "for s in final_chain.stream(\"how can langsmith help with testing\"):\n", 382 | " print(s, end=\"\")" 383 | ], 384 | "metadata": { 385 | "colab": { 386 | "base_uri": "https://localhost:8080/" 387 | }, 388 | "id": "t5PJMNbkbb3f", 389 | "outputId": "8a2bc828-4461-4a4f-ea19-5b5011d2e52c" 390 | }, 391 | "execution_count": 107, 392 | "outputs": [ 393 | { 394 | "output_type": "stream", 395 | "name": "stdout", 396 | "text": [ 397 | "LangSmith helps you test LLM applications in several ways:\n", 398 | "\n", 399 | "* **Evals** – The LangSmith SDK and UI let you build evaluation datasets and metrics, run those tests against your production traffic, score the results, and capture human feedback on the data. \n", 400 | "* **Observability** – Tracing, dashboards, and alerts give you real‑time visibility into key metrics (RPS, error rates, cost) so you can spot regressions or failures as soon as they happen. \n", 401 | "* **Prompt engineering** – Automatic version control and collaboration features let you iterate on prompts and see how changes affect test outcomes. \n", 402 | "\n", 403 | "Together, these tools give you a complete testing workflow that keeps your model’s quality high and your deployment confidence strong." 404 | ] 405 | } 406 | ] 407 | }, 408 | { 409 | "cell_type": "code", 410 | "source": [ 411 | "import gradio as gr" 412 | ], 413 | "metadata": { 414 | "id": "YWxfOOPHdy1L" 415 | }, 416 | "execution_count": 108, 417 | "outputs": [] 418 | }, 419 | { 420 | "cell_type": "code", 421 | "source": [ 422 | "def ask_langsmith(question):\n", 423 | " return \"\".join(final_chain.stream(question))\n", 424 | "\n", 425 | "with gr.Blocks() as demo:\n", 426 | " gr.Markdown(\"## 🧠 GPT-OSS RAG\")\n", 427 | "\n", 428 | " with gr.Row():\n", 429 | " inp = gr.Textbox(placeholder=\"Ask your question here...\", label=\"Your Question\")\n", 430 | " out = gr.Textbox(label=\"Answer\", lines=10)\n", 431 | "\n", 432 | " btn = gr.Button(\"Submit\")\n", 433 | " btn.click(fn=ask_langsmith, inputs=inp, outputs=out)" 434 | ], 435 | "metadata": { 436 | "id": "IHwhOvhVl0Ps" 437 | }, 438 | "execution_count": 109, 439 | "outputs": [] 440 | }, 441 | { 442 | "cell_type": "code", 443 | "source": [ 444 | "demo.launch(share=True)" 445 | ], 446 | "metadata": { 447 | "colab": { 448 | "base_uri": "https://localhost:8080/", 449 | "height": 612 450 | }, 451 | "id": "_vy76vYnl4n6", 452 | "outputId": "0905fe0a-d0b1-4a40-b7b1-af06b3389c45" 453 | }, 454 | "execution_count": 110, 455 | "outputs": [ 456 | { 457 | "output_type": "stream", 458 | "name": "stdout", 459 | "text": [ 460 | "Colab notebook detected. To show errors in colab notebook, set debug=True in launch()\n", 461 | "* Running on public URL: https://f797a586a559f805ff.gradio.live\n", 462 | "\n", 463 | "This share link expires in 1 week. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n" 464 | ] 465 | }, 466 | { 467 | "output_type": "display_data", 468 | "data": { 469 | "text/plain": [ 470 | "" 471 | ], 472 | "text/html": [ 473 | "
" 474 | ] 475 | }, 476 | "metadata": {} 477 | }, 478 | { 479 | "output_type": "execute_result", 480 | "data": { 481 | "text/plain": [] 482 | }, 483 | "metadata": {}, 484 | "execution_count": 110 485 | } 486 | ] 487 | }, 488 | { 489 | "cell_type": "code", 490 | "source": [], 491 | "metadata": { 492 | "id": "balbv-IKl6xp" 493 | }, 494 | "execution_count": null, 495 | "outputs": [] 496 | } 497 | ] 498 | } --------------------------------------------------------------------------------