{"id":23828620,"url":"https://github.com/gursv/langlens","last_synced_at":"2026-05-13T21:35:24.116Z","repository":{"id":261230341,"uuid":"883671457","full_name":"GURSV/LangLens","owner":"GURSV","description":"LangLens is an LLM model based on Openai gpt-3.5 and Salesforce vqa base model. For now, it can caption, detect objects in the image (perfectly) and answer some basic questions related to the image. ","archived":false,"fork":false,"pushed_at":"2024-11-23T17:21:12.000Z","size":6000,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-22T02:27:47.306Z","etag":null,"topics":["ai","captioning-images","gpt-3","huggingface-models","langchain-python","llms","object-detection","openai","openai-api","python","question-answering"],"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/GURSV.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":"2024-11-05T11:27:49.000Z","updated_at":"2024-11-23T17:21:15.000Z","dependencies_parsed_at":"2024-11-05T13:02:17.625Z","dependency_job_id":"a4e77a52-baac-4d57-9e0c-1515d352b319","html_url":"https://github.com/GURSV/LangLens","commit_stats":null,"previous_names":["gursv/langlens"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/GURSV/LangLens","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GURSV%2FLangLens","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GURSV%2FLangLens/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GURSV%2FLangLens/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GURSV%2FLangLens/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/GURSV","download_url":"https://codeload.github.com/GURSV/LangLens/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/GURSV%2FLangLens/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33001260,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-13T13:14:54.681Z","status":"ssl_error","status_checked_at":"2026-05-13T13:14:51.610Z","response_time":115,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["ai","captioning-images","gpt-3","huggingface-models","langchain-python","llms","object-detection","openai","openai-api","python","question-answering"],"created_at":"2025-01-02T13:20:09.000Z","updated_at":"2026-05-13T21:35:24.102Z","avatar_url":"https://github.com/GURSV.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LangLens ֎\n\nLangLens is an AI-powered model combining OpenAI's GPT, Salesforce's Visual Question Answering (VQA) base model, Fine Tuned Salesforce's VQA model \u0026 Facebook's detr-resnet-50. It offers the ability to:\n- Generate image captions.\n- Detect objects in images with high accuracy.\n- Answer basic image-related questions.\n\n## Features\n- **Image Captioning:** Provides detailed captions for uploaded images.\n- **Object Detection:** Identifies objects within images effectively.\n- **Question Answering:** Responds to queries about the content of an image.\n\n## Installation\n\n1. Clone the repository:\n   - git clone https://github.com/GURSV/LangLens.git\n   - cd LangLens\n\n2. Install dependencies:\n   - pip install -r requirements.txt\n\n## Usage\nRun the fine-tuning script:\n- python fine_tune_colab.py\n\nRun the main script:\n- python main.py\n\nThis will enable image processing and interactive question answering.\n\nAdditional utilities are provided in:\n- tools.py - Supplementary tools for model interaction.\n\nDataset:\n- The model uses a CSV dataset for fine-tuning. Ensure the dataset is formatted appropriately for training.\n\nImages folder:\n- images/ - For training the fine-tune model\n- images-for-test/ - For testing the project\n\nDo - streamlit run main.py for running the project locally (http://localhost:8501)\n\nView and working of the application\n\n![image](https://github.com/user-attachments/assets/4867d31b-9852-4495-b70f-9588b82675cd)\n\n![image](https://github.com/user-attachments/assets/eb4a22d1-466c-4edd-9eaf-b5b2d6f0a540)\n\n![image](https://github.com/user-attachments/assets/3812bb5c-aea3-4fca-b4e7-313fbaa8c20a)\n\n![image](https://github.com/user-attachments/assets/40a1c150-2ab3-4f47-9515-b78129848050)\n\n![image](https://github.com/user-attachments/assets/36d1ca7a-5956-46bb-8d3c-588deeed0c49)\n\netc...\n\nThank you.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgursv%2Flanglens","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgursv%2Flanglens","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgursv%2Flanglens/lists"}