{"id":19271217,"url":"https://github.com/alphasecio/groq","last_synced_at":"2025-08-03T03:34:37.196Z","repository":{"id":230638471,"uuid":"779867407","full_name":"alphasecio/groq","owner":"alphasecio","description":"A Streamlit chatbot with memory for running open-source text models on Groq.","archived":false,"fork":false,"pushed_at":"2025-07-12T04:54:04.000Z","size":929,"stargazers_count":2,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-07-19T21:16:58.082Z","etag":null,"topics":["gemma","groq","llama","mem0ai","mistral","python","streamlit"],"latest_commit_sha":null,"homepage":"https://groqqi.streamlit.app","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/alphasecio.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","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,"zenodo":null},"funding":{"ko_fi":"alphasec","buy_me_a_coffee":"alphasec"}},"created_at":"2024-03-31T02:09:12.000Z","updated_at":"2025-07-12T04:52:56.000Z","dependencies_parsed_at":"2024-03-31T03:21:52.685Z","dependency_job_id":"0d98f8b3-41f8-485a-ace3-edfe8626b91b","html_url":"https://github.com/alphasecio/groq","commit_stats":{"total_commits":16,"total_committers":2,"mean_commits":8.0,"dds":0.3125,"last_synced_commit":"792006be9d177c938c8c0652fb3cadc13e1ad8b9"},"previous_names":["alphasecio/groq"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/alphasecio/groq","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alphasecio%2Fgroq","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alphasecio%2Fgroq/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alphasecio%2Fgroq/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alphasecio%2Fgroq/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alphasecio","download_url":"https://codeload.github.com/alphasecio/groq/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alphasecio%2Fgroq/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266189676,"owners_count":23890065,"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":["gemma","groq","llama","mem0ai","mistral","python","streamlit"],"created_at":"2024-11-09T20:29:36.324Z","updated_at":"2025-08-03T03:34:37.188Z","avatar_url":"https://github.com/alphasecio.png","language":"Python","funding_links":["https://ko-fi.com/alphasec","https://buymeacoffee.com/alphasec"],"categories":[],"sub_categories":[],"readme":"# Groq Chatbot with Memory\n[Groq](https://groq.com) is a platform for running large language models (LLMs) with token-based pricing and no infrastructure management. Groq uses LPU Inference Engines, a new type of end-to-end processing unit system that provides fast inference for computationally intensive systems. This project showcases a Streamlit app using Groq-hosted models combined with [Mem0](https://github.com/mem0ai/mem0) for persistent conversational memory.\n\nSign up for an account at [GroqCloud](https://console.groq.com/keys) and get an API key, which you'll need for this project. You'll also need an [OpenAI API key](https://platform.openai.com/account/api-keys) for the embeddings model used by Mem0.\n\n![groq-playground](./groq-playground.png)\n\n### Supported Models\n* Groq (for chat response)\n  * `llama-3.3-70b-versatile`\n  * `meta-llama/llama-4-scout-17b-16e-instruct`\n  * `gemma2-9b-it`\n  * `mistral-saba-24b`\n  * `qwen-qwq-32b`\n  * `deepseek-r1-distill-llama-70b`\n* Mem0 (for memory backend)\n  * `mixtral-8x7b-32768`: for semantic memory retrieval\n  * `text-embedding-3-small`: for embeddings\n\n### Usage\n1. Clone the repository. Alternatively, deploy to [Railway](https://railway.app/?referralCode=alphasec), Render, or Google Cloud Run.\n```bash\ngit clone https://github.com/alphasecio/groq.git\ncd groq\n```\n2. Set your API keys either as environment variables or via the Streamlit sidebar inputs.\n3. Run the app.\n```bash\nstreamlit run streamlit_app.py\n````\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falphasecio%2Fgroq","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falphasecio%2Fgroq","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falphasecio%2Fgroq/lists"}