{"id":15638088,"url":"https://github.com/anakin87/mistral-haystack","last_synced_at":"2025-04-14T19:43:23.241Z","repository":{"id":197110507,"uuid":"697992068","full_name":"anakin87/mistral-haystack","owner":"anakin87","description":" Mistral + Haystack: build RAG pipelines that rock 🤘","archived":false,"fork":false,"pushed_at":"2024-02-07T16:27:10.000Z","size":246,"stargazers_count":103,"open_issues_count":0,"forks_count":10,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-03-28T08:04:29.240Z","etag":null,"topics":["haystack","large-language-models","llm","rag","retrieval-augmented-generation"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/anakin87.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-09-28T22:49:53.000Z","updated_at":"2025-03-07T09:07:57.000Z","dependencies_parsed_at":"2023-09-29T02:24:53.531Z","dependency_job_id":"52735b6c-b0a3-4dc6-82cc-ad248432af52","html_url":"https://github.com/anakin87/mistral-haystack","commit_stats":null,"previous_names":["anakin87/mistral-haystack"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anakin87%2Fmistral-haystack","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anakin87%2Fmistral-haystack/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anakin87%2Fmistral-haystack/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anakin87%2Fmistral-haystack/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anakin87","download_url":"https://codeload.github.com/anakin87/mistral-haystack/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248949417,"owners_count":21188068,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["haystack","large-language-models","llm","rag","retrieval-augmented-generation"],"created_at":"2024-10-03T11:18:04.843Z","updated_at":"2025-04-14T19:43:23.212Z","avatar_url":"https://github.com/anakin87.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 📌 mistral-haystack collection\n **Mistral + Haystack Collection: build RAG pipelines that rock 🤘**\n\n Collection of notebooks and resources to build Retrieval Augmented Generation pipelines using:\n - [Mistral](https://mistral.ai/) models 🤖\n - [Haystack](https://github.com/deepset-ai/haystack) LLM orchestration framework 🏗️.\n\n\n \u003cimg src=\"https://static.otta.com/uploads/images/company-logos/17023-r1fn8E7CIWJX0L-iFw8YivXD9C37itYuFvVWW_xFh5k.svg\" width=\"270\" style=\"display:inline;\"\u003e\u003cimg src=\"https://img.freepik.com/premium-vector/electric-guitar-fire-hot-rock-music-guitar-flames-hard-rock-rock-roll-concert-festival-label-night-club-live-show-vector-logo-emblem_570429-23178.jpg?w=2000\" width=\"180\"\u003e\u003cimg src=\"https://haystack.deepset.ai/images/haystack-ogimage.png\" width=\"360\" style=\"display:inline;\"\u003e\n\n 💻 **For other great Haystack Notebooks, check out the 👩🏻‍🍳 [Haystack Cookbook](https://github.com/deepset-ai/haystack-cookbook)**\n\n\n## 📓 Notebooks\n\n| **Model**                | **Haystack version** | **Link** | **Details**                                             | **Author** |\n|--------------------------|----------------------|----------|---------------------------------------------------------|------------|\n| Mistral-7B-Instruct-v0.1 | 1.x                  |  [🎸 Notebook](mistral_haystack.ipynb) | RAG on a collection of Rock music resources, using the free Hugging Face Inference API | [@anakin87](https://github.com/anakin87)   |\n| Mixtral-8x7B-Instruct-v0.1 | 1.x                  |  [📄🚀 Notebook](https://colab.research.google.com/drive/1rH8df-C3P9pL4yrC2qSae9IOtx5Mr1N_) | RAG on a PDF File, using the free Hugging Face Inference API (using the free Hugging Face Inference API) | [@AlessandroDiLauro](https://github.com/alessandrodilauro)   |\n| Mixtral-8x7B-Instruct-v0.1 | 1.x                  |  [🛒 Notebook](https://colab.research.google.com/drive/1LGaA2TcabnqU6jNrI6i598BeYWAX_xU-) \u003cbr/\u003e [📊🔍 Blog post](https://medium.com/@alessandrodilauro72/enhancing-csv-data-retrieval-and-product-description-analysis-with-haystacks-retrieval-augmented-89140237110c) | RAG from CSV, Product description analysis | [@AlessandroDiLauro](https://github.com/alessandrodilauro)   |\n| Mixtral-8x7B-Instruct-v0.1 | 2.x                  |  [🕸️💬 Notebook](https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/notebooks/mixtral-8x7b-for-web-qa.ipynb) | RAG on the Web, using the free Hugging Face Inference API | [@TuanaCelik](https://github.com/tuanacelik)   |\n| Zephyr-7B Beta | 2.x                  |  [🪁 Article and notebook](https://haystack.deepset.ai/blog/guide-to-using-zephyr-with-haystack2) | Article on how make  this great model (fine-tuned from Mistral) run locally on Colab | [@TuanaCelik](https://github.com/tuanacelik) [@anakin87](https://github.com/anakin87)   |\n| Mixtral-8x7B-Instruct-v0.1 | 2.x                  |  [🩺💬 Article and notebook](https://haystack.deepset.ai/blog/mixtral-8x7b-healthcare-chatbot) | Healthcare chatbot with Mixtral, Haystack, and PubMed | [@annthurium](https://github.com/annthurium)   | |\n| Mixtral-8x7B-Instruct-v0.1 | 2.x                  |  [🇮🇹🇬🇧🎧 Notebook](https://github.com/deepset-ai/haystack-cookbook/blob/main/notebooks/multilingual_rag_podcast.ipynb) | Multilingual RAG from a podcast | [@anakin87](https://github.com/anakin87)   | |\n| Mixtral-8x7B-Instruct-v0.1 | 2.x                  |  [📰 Notebook](https://colab.research.google.com/drive/1mp4MVQEAFZ0Zz2AI9aJ1uOHJ5k73B2fr?usp=sharing) | Building a Hacker News Top Stories TL;DR | [@TuanaCelik](https://github.com/tuanacelik)  | |\n\n## 📚 Resources\n\n- [Mixture of Experts Explained](https://huggingface.co/blog/moe)\n\n  Great and deep blog post by Hugging Face on the MoE architecture, which is the basis of Mistral 8x7B.\n\n- [Zephyr: Direct Distillation of LM Alignment](https://arxiv.org/abs/2310.16944)\n  \n  Technical report by the Hugging Face H4 team.\n  They explain how they trained Zephyr, a strong 7B model fine-tuned from Mistral.\n  \n  The main topic is: ⚗️ **how to effectively distill the capabilities of GPT-4 into smaller models?**\n  The report is insightful and well worth reading. I have summarized it [here](https://www.linkedin.com/posts/stefano-fiorucci_llm-largelanguagemodels-nlp-activity-7129738807934885888-ADEX).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanakin87%2Fmistral-haystack","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanakin87%2Fmistral-haystack","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanakin87%2Fmistral-haystack/lists"}