{"id":29131385,"url":"https://github.com/giovaneiwamoto/capiara-code-mentor","last_synced_at":"2025-06-30T05:33:01.541Z","repository":{"id":290879082,"uuid":"940379827","full_name":"GiovaneIwamoto/capiara-code-mentor","owner":"GiovaneIwamoto","description":"🦜 CapIAra Code Mentor - Learn to think, not just code! Develop real problem-solving skills by mastering algorithmic logic step by step. Strengthen your reasoning, break down complex challenges, and build a solid foundation for programming without relying on ready-made code.","archived":false,"fork":false,"pushed_at":"2025-06-09T17:07:51.000Z","size":720,"stargazers_count":2,"open_issues_count":4,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-09T18:23:27.943Z","etag":null,"topics":["agent","code","langchain","llm","maritalk","mentor","streamlit"],"latest_commit_sha":null,"homepage":"","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/GiovaneIwamoto.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"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}},"created_at":"2025-02-28T04:27:23.000Z","updated_at":"2025-06-09T17:07:54.000Z","dependencies_parsed_at":"2025-06-09T18:33:20.150Z","dependency_job_id":null,"html_url":"https://github.com/GiovaneIwamoto/capiara-code-mentor","commit_stats":null,"previous_names":["giovaneiwamoto/capiara-code-mentor"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/GiovaneIwamoto/capiara-code-mentor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GiovaneIwamoto%2Fcapiara-code-mentor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GiovaneIwamoto%2Fcapiara-code-mentor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GiovaneIwamoto%2Fcapiara-code-mentor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GiovaneIwamoto%2Fcapiara-code-mentor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GiovaneIwamoto","download_url":"https://codeload.github.com/GiovaneIwamoto/capiara-code-mentor/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GiovaneIwamoto%2Fcapiara-code-mentor/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262719969,"owners_count":23353411,"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":["agent","code","langchain","llm","maritalk","mentor","streamlit"],"created_at":"2025-06-30T05:32:58.904Z","updated_at":"2025-06-30T05:33:01.507Z","avatar_url":"https://github.com/GiovaneIwamoto.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg width=\"1033\" alt=\"image\" src=\"https://github.com/user-attachments/assets/2e877b62-077a-48e4-8ecc-175788ec1a4b\" /\u003e\n\n# Installation Guide\n\n- Install required dependencies\n```shell\npip install -r requirements.txt\n```\n\n- Run Streamlit\n```shell\nstreamlit run app.py\n```\n\n# Documentation - Langchain\n\n- Conceptual Guide\n\nhttps://python.langchain.com/v0.2/docs/concepts/\n\n- Callbacks\n\nhttps://python.langchain.com/v0.2/docs/concepts/#callbacks\n\n- Streaming\n\nhttps://python.langchain.com/v0.2/docs/concepts/#streaming\n\n- Message Persistence\n\nhttps://python.langchain.com/docs/tutorials/chatbot/#message-persistence\n\n- Managing Conversation History\n\nhttps://python.langchain.com/docs/tutorials/chatbot/#managing-conversation-history\n\n- Trim Messages\n\nhttps://python.langchain.com/api_reference/core/messages/langchain_core.messages.utils.trim_messages.html\n\n- Retrieval Augmented Generation\n\nhttps://python.langchain.com/docs/tutorials/rag/#setup\n\nhttps://python.langchain.com/docs/tutorials/qa_chat_history/\n\n- Retrieval Concept\n\nhttps://python.langchain.com/docs/concepts/retrieval/\n\n- Retrievers\n\nhttps://python.langchain.com/docs/concepts/retrievers/\n\n- Vector Store\n\nhttps://python.langchain.com/docs/concepts/vectorstores/\n\n- Embedding Models\n\nhttps://python.langchain.com/docs/concepts/embedding_models/\n\n- Ollama Embeddings\n\nhttps://python.langchain.com/docs/integrations/text_embedding/ollama/\n\n- Pinecone Vector Store\n\nhttps://python.langchain.com/api_reference/pinecone/vectorstores/langchain_pinecone.vectorstores.PineconeVectorStore.html#langchain_pinecone.vectorstores.PineconeVectorStore\n\n- Recursive Text Splitter\n\nhttps://python.langchain.com/docs/how_to/recursive_text_splitter/\n\n- Document Base\n\nhttps://python.langchain.com/api_reference/core/documents/langchain_core.documents.base.Document.html\n\n- Tool Calling\n\nhttps://python.langchain.com/docs/concepts/tool_calling/\n\nhttps://blog.langchain.dev/tool-calling-with-langchain/\n\n- Tool Artifacts\n\nhttps://python.langchain.com/docs/how_to/tool_artifacts/\n\n- Structured Output\n\nhttps://python.langchain.com/docs/how_to/structured_output/\n\n- Chat OpenAI\n\nhttps://python.langchain.com/docs/integrations/chat/openai/\n\n# Documentation - Maritalk\n\n- Models\n\nhttps://docs.maritaca.ai/pt/modelos\n\n- Rate Limits\n\nhttps://docs.maritaca.ai/pt/rate-limits\n\n- Embedding and RAG\n\nhttps://docs.maritaca.ai/pt/embeddings+Sabia-3+RAG\n\n- Tool Calling\n\nhttps://docs.maritaca.ai/pt/chamada-funcao\n\n# Documentation - Ollama\n\n- Meta Llama 3\n\nhttps://ollama.com/library/llama3/blobs/6a0746a1ec1a\n\n```shell\nollama run llama3\n```\n- Nomic Embed Text\n\nhttps://ollama.com/library/nomic-embed-text\n\n```shell\nollama pull nomic-embed-text\n```\n\n# Documentation - Nomic\n\n- HuggingFace \n\nhttps://huggingface.co/nomic-ai/nomic-embed-text-v1.5\n\n- Blog\n\nhttps://www.nomic.ai/blog/posts/nomic-embed-text-v1\n\n# Documentation - LangSmith\n\nhttps://docs.smith.langchain.com\n\n# Info - AI Powered Search\n\n- The Basics of AI-Powered Vector Search\n\nhttps://cameronrwolfe.substack.com/p/the-basics-of-ai-powered-vector-search?utm_source=profile\u0026utm_medium=reader2\n\n- LLM Powered Autonomous Agents\n\nhttps://lilianweng.github.io/posts/2023-06-23-agent/\n\n# Documentation - Prompt Engineering \n\n- AWS Prompt Engineering Best Practices\n\nhttps://docs.aws.amazon.com/prescriptive-guidance/latest/llm-prompt-engineering-best-practices/introduction.html\n\n- AWS Common prompt injection attacks\n\nhttps://docs.aws.amazon.com/prescriptive-guidance/latest/llm-prompt-engineering-best-practices/common-attacks.html\n\n- IBM Prompt Injection\n\nhttps://www.ibm.com/think/topics/prompt-injection\n\n# About \n\n| **Use Case**          | **chunk_size**    | **chunk_overlap** | **Justification** |\n|-----------------------|-------------------|-------------------|--------------------|\n| **Short Queries**     | 500 - 1000        | 100 - 200         | Improves semantic search accuracy without overly fragmenting the context. |\n| **Long Documents**    | 1000 - 2000       | 200 - 300         | Prevents context loss when splitting large documents. |\n| **Source Code**       | 300 - 600         | 50 - 100          | Smaller chunks help avoid losing critical information. |","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgiovaneiwamoto%2Fcapiara-code-mentor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgiovaneiwamoto%2Fcapiara-code-mentor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgiovaneiwamoto%2Fcapiara-code-mentor/lists"}