{"id":18798588,"url":"https://github.com/liteobject/embeddings_with_chromadb","last_synced_at":"2026-01-02T02:30:15.951Z","repository":{"id":239859067,"uuid":"800797395","full_name":"LiteObject/embeddings_with_chromadb","owner":"LiteObject","description":null,"archived":false,"fork":false,"pushed_at":"2024-07-09T19:25:51.000Z","size":37,"stargazers_count":0,"open_issues_count":6,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-29T18:21:21.957Z","etag":null,"topics":["chromadb","embeddings","llm","vector-database"],"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/LiteObject.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":"2024-05-15T02:41:55.000Z","updated_at":"2024-05-15T03:38:17.000Z","dependencies_parsed_at":"2024-12-29T18:20:58.178Z","dependency_job_id":"edd59508-2e84-4e15-ada4-4bfc3122d6db","html_url":"https://github.com/LiteObject/embeddings_with_chromadb","commit_stats":null,"previous_names":["liteobject/embeddings_with_chromadb"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiteObject%2Fembeddings_with_chromadb","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiteObject%2Fembeddings_with_chromadb/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiteObject%2Fembeddings_with_chromadb/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LiteObject%2Fembeddings_with_chromadb/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LiteObject","download_url":"https://codeload.github.com/LiteObject/embeddings_with_chromadb/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239727055,"owners_count":19687099,"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":["chromadb","embeddings","llm","vector-database"],"created_at":"2024-11-07T22:12:25.781Z","updated_at":"2026-01-02T02:30:15.796Z","avatar_url":"https://github.com/LiteObject.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Embeddings with Chromadb\nEmbeddings have revolutionized the way we represent and process data in machine learning and natural language processing tasks. They allow us to transform high-dimensional, unstructured data into compact, meaningful vector representations. ChromaDB, a powerful vector database, takes embeddings to the next level by providing efficient storage, retrieval, and similarity search capabilities. In this blog post, we'll explore how ChromaDB empowers developers to harness the full potential of embeddings.\n\n## What is embeddings?\n\n## Setup Chroma DB\n\n### Install chromadb package\n    pip install chromadb\n\n### Get the chroma client\n    import chromadb\n    chroma_client = chromadb.Client()\n\n### Create a collection\nCollections are where you'll store your embeddings, documents, and any additional metadata. You can create a collection with a name:\n\n    collection = chroma_client.create_collection(name=\"my_collection\")\n\n### Add some text documents to the collection\nChroma will store your text and handle embedding and indexing automatically. You can also customize the embedding model.\n\n```python\n    collection.add(\n        documents=[\n            \"This is a document about pineapple\",\n            \"This is a document about oranges\"\n        ],\n        ids=[\"id1\", \"id2\"]\n    )\n```\n\n###  Query the collection\n\n```python\nresults = collection.query(\n    query_texts=[\"This is a query document about hawaii\"], # Chroma will embed this for you\n    n_results=2 # how many results to return\n)\nprint(results)\n```\n\n### Inspect Results\n\n\n## Links\n- [ChromaDB: Getting Started](https://docs.trychroma.com/getting-started)\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fliteobject%2Fembeddings_with_chromadb","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fliteobject%2Fembeddings_with_chromadb","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fliteobject%2Fembeddings_with_chromadb/lists"}