{"id":20345816,"url":"https://github.com/izzypt/context_ai","last_synced_at":"2025-08-11T23:17:22.132Z","repository":{"id":208452922,"uuid":"712520329","full_name":"izzypt/Context_AI","owner":"izzypt","description":"Exploring langchain and it's application to LLM application","archived":false,"fork":false,"pushed_at":"2023-11-22T19:43:16.000Z","size":15,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-04T15:48:02.327Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","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/izzypt.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":"2023-10-31T16:20:40.000Z","updated_at":"2023-11-21T22:09:30.000Z","dependencies_parsed_at":"2025-01-14T21:34:45.332Z","dependency_job_id":"93b9e2f3-3e7d-4607-9ba1-a86aab2dfddb","html_url":"https://github.com/izzypt/Context_AI","commit_stats":null,"previous_names":["izzypt/legal_ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/izzypt/Context_AI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/izzypt%2FContext_AI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/izzypt%2FContext_AI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/izzypt%2FContext_AI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/izzypt%2FContext_AI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/izzypt","download_url":"https://codeload.github.com/izzypt/Context_AI/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/izzypt%2FContext_AI/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269970129,"owners_count":24505472,"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","status":"online","status_checked_at":"2025-08-11T02:00:10.019Z","response_time":75,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":[],"created_at":"2024-11-14T22:09:52.546Z","updated_at":"2025-08-11T23:17:22.056Z","avatar_url":"https://github.com/izzypt.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI_Document_Reader\n\nThis project explores langchain and llm based apps. \n\nThe goal is to create an app that takes user input/context data like PDF's and provides it as context to a LLM. \n\nLangchain is an AI first framework, that enables developers to build context aware reasoning apps by linking LLM's with external data sources for advanced NLP apps.\n\n# Embedding and Vector Databases\n\n### Theory\n  \n![image](https://github.com/izzypt/Legal_AI/assets/73948790/55b8cd66-4cff-4b2f-91c6-2bd28819bc8c)\n\n- Starting from the PDF position of the image above:\n  - We are going to be taking the PDF's from our user and break them down into chunks of strings\n  - Later we going to convert those chuncks into embeddings (embeddings are vector representation of the text/ contains information about the meaning of the text)\n  - Those embeddings are stored in a vector store (knowledge base/vector database)\n\n- Starting from the user position of the image above:\n  - Once we have our DB we can take questions from the user:\n  - He asks some question like \"What is a neural network\" and we embedd his question into vectors/numerical representation using the same algorithm we used to embedd the PDF'S into chunks of text.\n  - With this we can make a semantic search, allowing us to find in the DB the vectors that have similar meaning to our question.\n  - This will give us a rank of results that are relevant.\n  - Those results we will give them to the LLM which will, in turn, return us an answer.\n\n### Use\n\nEnsure that you have installed the required dependencies and added the OpenAI API key to the .env file.\n\nRun the main.py file using the Streamlit CLI. Execute the following command:\n\n```\nstreamlit run app.py\n```\nThe application will launch in your default web browser, displaying the user interface.\n\nLoad multiple PDF documents into the app by following the provided instructions.\n\nAsk questions in natural language about the loaded PDFs using the chat interface.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fizzypt%2Fcontext_ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fizzypt%2Fcontext_ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fizzypt%2Fcontext_ai/lists"}