{"id":15707838,"url":"https://github.com/anakin87/try-agents-haystack","last_synced_at":"2025-05-12T19:52:29.951Z","repository":{"id":240859382,"uuid":"623548633","full_name":"anakin87/try-agents-haystack","owner":"anakin87","description":"Trying the Agents 🕵️ --\u003e new feature introduced in Haystack 1.15.0 to make Large Language Models resolve complex queries and tasks","archived":false,"fork":false,"pushed_at":"2023-04-05T10:03:30.000Z","size":2525,"stargazers_count":5,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-01T02:52:49.528Z","etag":null,"topics":["generative-ai","haystack","language-model","large-language-models","natural-language-processing","nlp"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"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":"2023-04-04T15:35:01.000Z","updated_at":"2024-10-13T12:08:20.000Z","dependencies_parsed_at":"2024-05-21T06:13:12.408Z","dependency_job_id":null,"html_url":"https://github.com/anakin87/try-agents-haystack","commit_stats":null,"previous_names":["anakin87/try-agents-haystack"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anakin87%2Ftry-agents-haystack","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anakin87%2Ftry-agents-haystack/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anakin87%2Ftry-agents-haystack/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/anakin87%2Ftry-agents-haystack/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/anakin87","download_url":"https://codeload.github.com/anakin87/try-agents-haystack/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253811969,"owners_count":21968190,"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":["generative-ai","haystack","language-model","large-language-models","natural-language-processing","nlp"],"created_at":"2024-10-03T20:41:31.165Z","updated_at":"2025-05-12T19:52:29.927Z","avatar_url":"https://github.com/anakin87.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# try-agents-haystack\nTrying the Agents 🕵️ --\u003e new feature introduced in [Haystack](https://github.com/deepset-ai/haystack) 1.15.0 to make Large Language Models resolve complex queries and tasks.\n\n---\nAs of release 1.15, Haystack implements Agents 🕵️!\n\nPut simply, an Agent is a Large Language Model with a specific prompt.\n\nBased on that prompt, the Agent can answer complex questions, by performing a sequence of steps.\n\nAt each step, the Agent (our brain 🧠) can select a Tool from its toolbox 🧰 and use it to accomplish a task.\n\nSome examples of Tools: Web Search, calculator, several pipelines/nodes (available in Haystack)...\n\n## Demo\nhttps://user-images.githubusercontent.com/44616784/229845195-c2d6f5a5-8354-4816-aa21-6e29c06b149f.mp4\n\n\nIn the video, you see the Agent in action with the task of answering questions about books on my reading list.\n\n* I uploaded a CSV containing a minimal reading list 📚\n* I initialized two Tools ⚒️:\n    * A Question Answering component to answer questions about my reading list\n    * A Search tool 🔎🌐, which can browse the web and find information\n* I defined an Agent, based on Davinci model and equipped with the Tools defined above.\n* Now I can ask complex questions, such as \"Can you provide me with information on the shortest book on my reading list, including author and price on Amazon?\"\"\n\n🚀\n\nCurrently, Agents work great with OpenAI Davinci model.\nSoon, open-source models will also be supported, so you can have the power of LLM at your disposal without giving up your data!\n\n## More information\n### Agents in Haystack\n- [Introducing Agents in Haystack: Make LLMs resolve complex tasks](https://haystack.deepset.ai/blog/introducing-haystack-agents) by Tuana Çelik\n- [Tutorial: Answering Multihop Questions with Agents](https://haystack.deepset.ai/tutorials/23_answering_multihop_questions_with_agents)\n- [Haystack documentation: the Agent](https://docs.haystack.deepset.ai/docs/agent)\n\n### Papers\n- [ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629)\n- [MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning](https://arxiv.org/abs/2205.00445)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanakin87%2Ftry-agents-haystack","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fanakin87%2Ftry-agents-haystack","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fanakin87%2Ftry-agents-haystack/lists"}