After finishing the Quickstart, most developers want to go further. In our docs site. we’ve collected hands-on examples with Pinecone and common AI patterns, tools, and algorithms:
| Example | Model(s) | Stack |
|---|---|---|
| Semantic Search | ||
| How to perform a simple semantic search. | all-MiniLM-L6-v2 | PythonSentence Transformers |
| Semantic Search - Typescript | ||
| A simple semantic search app in TypeScript | all-MiniLM-L6-v2 | TypeScriptSentence Transformers |
| Semantic Search - AWS Reference Architecture with Pulumi | ||
| Use the official AWS Reference Architecture as a starting point for high-scale semantic search apps. | all-MiniLM-L6-v2 | TypeScriptTransformers.jsAWSPulumiReact |
| Generative QA with OpenAI | ||
| Build retrieval enhanced generative QA systems with OpenAI. | text-davinci-003text-embedding-ada-002 | PythonOpenAI |
| Article Recommender - Typescript | ||
| Use Pinecone to create a simple personalized article or content recommender in Typescript. | all-MiniLM-L6-v2 | TypeScriptTransformers.jsDanfo.js |
| Chatbot Agents with LangChain | ||
| How to create conversational agents with LangChain and Pinecone. | gpt-3.5-turbotext-embedding-ada-002 | PythonOpenAILangChain |
| Chatbot Agents with LangChain - Typescript | ||
| How to create conversational agents with LangChain and Pinecone. | gpt-3.5-turboall-MiniLM-L6-v2 | TypeScriptOpenAILangChainTransformers.jsDanfo.js |
| Langchain Retrieval Augmentation | ||
| How to give knowledge base information to an LLM using LangChain. | gpt-3.5-turbotext-embedding-ada-002 | LangchainOpenAIPython |
| GPT4 with Retrieval Augmentation over LangChain docs | ||
| How to use GPT-4 with retrieval augmentation to answer questions. | gpt-4text-embedding-ada-002 | LangchainOpenAIPython |
| Image Search - Typescript | ||
| Use Pinecone to create an image search engine with Typescript. | clip-vit-base-patch32 | TypeScriptTransformers.jsReact |