:::callout{intent="warning" title="Deprecated integrations"} ### OctoAI integrations are deprecated OctoAI announced that they are winding down the commercial availability of its services by **31 October 2024**. Accordingly, the Weaviate OctoAI integrations are deprecated. Do not use these integrations for new projects. From Weaviate `v1.25.22`, `v1.26.8`, and `v1.27.1`, the `text2vec-octoai` and `generative-octoai` modules are inactive. Every vectorization and generation request they receive fails server-side with the error `OctoAI is permanently shut down`. The configuration, import, search, and RAG examples on these pages therefore no longer run against OctoAI, and are kept only as a record of how the integrations used to be configured. Of the options below, only "bring your own vectors" (Option 1) keeps an existing OctoAI collection usable. If you have a collection that is using an OctoAI integration, consider your options depending on whether you are using OctoAI's embedding models ([your options](#for-collections-with-octoai-embedding-integrations)) or generative models ([your options](#for-collections-with-octoai-generative-ai-integrations)). #### For collections with OctoAI embedding integrations OctoAI provided `thenlper/gte-large` as the embedding model. This model is also available through the [Hugging Face API](huggingface-embeddings.md). After the shutdown date, this model will no longer be available through OctoAI. If you are using this integration, you have the following options: **Option 1: Use the existing collection, and provide your own vectors** You can continue to use the existing collection, provided that you rely on some other method to generate the required embeddings yourself for any new data, and for queries. If you are unfamiliar with the "bring your own vectors" approach, [refer to this starter guide](../starter-guides/custom-vectors.md). **Option 2: Migrate to a new collection with another model provider** Alternatively, you can migrate your data to a new collection ([read how](#how-to-migrate)). At this point, you can re-use the existing embeddings or choose a new model. - **Re-using the existing embeddings** will save on time and inference costs. - **Choosing a new model** will allow you to explore new models and potentially improve the performance of your application. If you would like to re-use the existing embeddings, you must select a model provider (e.g. [Hugging Face API](huggingface-embeddings.md)) that offers the same embedding model. You can also select a new model with any embedding model provider. This will require you to re-generate the embeddings for your data, as the existing embeddings will not be compatible with the new model. #### For collections with OctoAI generative AI integrations If you are only using the generative AI integration, you do not need to migrate your data to a new collection. Follow [this how-to](../how-to-manage-collections/generative-reranker-models.md#update-the-generative-model-integration) to re-configure your collection with a new generative AI model provider. Note this requires Weaviate `v1.25.23`, `v1.26.8`, `v1.27.1`, or later. You can select any model provider that offers generative AI models. If you would like to continue to use the same model that you used with OctoAI, providers such as [Anyscale](anyscale-generative.md), [FriendliAI](friendliai-generative.md), [Mistral](mistral-generative.md) or local models with [Ollama](ollama-generative.md) each offer some of the suite of models that OctoAI provided. #### How to migrate An outline of the migration process is as follows: - Create a new collection with the desired model provider integration(s). - Export the data from the existing collection. - (Optional) To re-use the existing embeddings, export the data with the existing embeddings. - Import the data into the new collection. - (Optional) To re-use the existing embeddings, import the data with the existing embeddings. - Update your application to use the new collection. See [How-to manage data: migrate data](../how-to-manage-collections/migrate.md) for examples on migrating data objects between collections. ::: # OctoAI Generative AI with Weaviate Weaviate's integration with OctoAI's APIs allows you to access open source and their models' capabilities directly from Weaviate. [Configure a Weaviate collection](#configure-collection) to use a generative AI model with OctoAI. Weaviate will perform retrieval augmented generation (RAG) using the specified model and your OctoAI API key. More specifically, Weaviate will perform a search, retrieve the most relevant objects, and then pass them to the OctoAI generative model to generate outputs. ![RAG integration illustration](/assets/docs/weaviate/model-providers/_includes/integration_octoai_rag.png) ## Requirements ### Weaviate configuration Your Weaviate instance must be configured with the OctoAI generative AI integration (`generative-octoai`) module. :::accordion{title="For Weaviate Cloud (WCD) users"} This integration is enabled by default on Weaviate Cloud (WCD) instances. ::: :::accordion{title="For self-hosted users"} - Check the [cluster metadata](../monitoring-and-logging/status.md#cluster-metadata) to verify if the module is enabled. - Follow the [how-to configure modules](../how-to-configure-weaviate/modules.md) guide to enable the module in Weaviate. ::: ### API credentials You must provide a valid OctoAI API key to Weaviate for this integration. Go to [OctoAI](https://octo.ai/docs/getting-started/how-to-create-an-octoai-access-token) to sign up and obtain an API key. Provide the API key to Weaviate using one of the following methods: - Set the `OCTOAI_APIKEY` environment variable that is available to Weaviate. - Provide the API key at runtime, as shown in the examples below. :::code-group{sync="languages"} ```python title="Python" # Recommended: save sensitive data as environment variables octoai_key = os.getenv("OCTOAI_API_KEY") ``` ```typescript title="JavaScript/TypeScript" const octoaiApiKey = process.env.OCTOAI_API_KEY || ''; // Replace with your inference API key ``` ::: ## Configure collection :::callout{intent="info" title="Generative model integration mutability"} A collection's `generative` model integration configuration is mutable from `v1.25.23`, `v1.26.8` and `v1.27.1`. See [this section](../how-to-manage-collections/generative-reranker-models.md#update-the-generative-model-integration) for details on how to update the collection configuration. ::: [Configure a Weaviate index](../how-to-manage-collections/generative-reranker-models.md#specify-a-generative-model-integration) as follows to use an OctoAI generative AI model: :::code-group{sync="languages"} ```python title="Python" from weaviate.classes.config import Configure client.collections.create( "DemoCollection", generative_config=Configure.Generative.octoai() # Additional parameters not shown ) ``` ```typescript title="JavaScript/TypeScript" {3} await client.collections.create({ name: 'DemoCollection', generative: weaviate.configure.generative.octoai(), // Additional parameters not shown }); ``` ::: ### Select a model You can specify one of the [available models](#available-models) for Weaviate to use, as shown in the following configuration example: :::code-group{sync="languages"} ```python title="Python" from weaviate.classes.config import Configure client.collections.create( "DemoCollection", generative_config=Configure.Generative.octoai( model="meta-llama-3-70b-instruct" ) # Additional parameters not shown ) ``` ```typescript title="JavaScript/TypeScript" {3-5} await client.collections.create({ name: 'DemoCollection', generative: weaviate.configure.generative.octoai({ model: 'meta-llama-3-70b-instruct' }), // Additional parameters not shown }); ``` ::: You can [specify](#generative-parameters) one of the [available models](#available-models) for Weaviate to use. The [default model](#available-models) is used if no model is specified. ### Generative parameters Configure the following generative parameters to customize the model behavior. :::code-group{sync="languages"} ```python title="Python" from weaviate.classes.config import Configure client.collections.create( "DemoCollection", generative_config=Configure.Generative.octoai( # # These parameters are optional model = "meta-llama-3-70b-instruct", max_tokens = 500, temperature = 0.7, base_url = "https://text.octoai.run" ) ) ``` ```typescript title="JavaScript/TypeScript" {3-8} await client.collections.create({ name: 'DemoCollection', generative: weaviate.configure.generative.octoai({ model: 'meta-llama-3-70b-instruct', maxTokens: 500, temperature: 0.7, baseURL: 'https://text.octoai.run' }), // Additional parameters not shown }); ``` ::: For further details on model parameters, see the [OctoAI API documentation](https://octo.ai/docs/text-gen-solution/rest-api). ## Retrieval augmented generation After configuring the generative AI integration, perform RAG operations, either with the [single prompt](#single-prompt) or [grouped task](#grouped-task) method. ### Single prompt ![Single prompt RAG integration generates individual outputs per search result](/assets/docs/weaviate/model-providers/_includes/integration_octoai_rag_single.png) To generate text for each object in the search results, use the single prompt method. The example below generates outputs for each of the `n` search results, where `n` is specified by the `limit` parameter. When creating a single prompt query, use braces `{}` to interpolate the object properties you want Weaviate to pass on to the language model. For example, to pass on the object's `title` property, include `{title}` in the query. :::code-group{sync="languages"} ```python title="Python" {5-6} collection = client.collections.use("DemoCollection") response = collection.generate.near_text( query="A holiday film", # The model provider integration will automatically vectorize the query single_prompt="Translate this into French: {title}", limit=2 ) for obj in response.objects: print(obj.properties["title"]) print(f"Generated output: {obj.generated}") # Note that the generated output is per object ``` ```typescript title="JavaScript/TypeScript" let response; const myCollection = client.collections.use("DemoCollection"); ``` ::: ### Grouped task ![Grouped task RAG integration generates one output for the set of search results](/assets/docs/weaviate/model-providers/_includes/integration_octoai_rag_grouped.png) To generate one text for the entire set of search results, use the grouped task method. In other words, when you have `n` search results, the generative model generates one output for the entire group. :::code-group{sync="languages"} ```python title="Python" {5-6} collection = client.collections.use("DemoCollection") response = collection.generate.near_text( query="A holiday film", # The model provider integration will automatically vectorize the query grouped_task="Write a fun tweet to promote readers to check out these films.", limit=2 ) print(f"Generated output: {response.generative.text}") # Note that the generated output is per query for obj in response.objects: print(obj.properties["title"]) ``` ```typescript title="JavaScript/TypeScript" let response; const myCollection = client.collections.use("DemoCollection"); ``` ::: ## References ### Available models - `qwen1.5-32b-chat` - `meta-llama-3-8b-instruct` - `meta-llama-3-70b-instruct` - `mixtral-8x22b-instruct` - `nous-hermes-2-mixtral-8x7b-dpo` - `mixtral-8x7b-instruct` - `mixtral-8x22b-finetuned` - `hermes-2-pro-mistral-7b` - `mistral-7b-instruct` (default) - `codellama-7b-instruct` - `codellama-13b-instruct` - `codellama-34b-instruct` - `llama-2-13b-chat` - `llama-2-70b-chat` ## Further resources ### Other integrations - [OctoAI embedding models + Weaviate](octoai-embeddings.md). ### Code examples Once the integrations are configured at the collection, the data management and search operations in Weaviate work identically to any other collection. See the following model-agnostic examples: - The [How-to: Manage collections](../how-to-manage-collections/index.md) and [How-to: Manage objects](../how-to-manage-objects/index.md) guides show how to perform data operations (i.e. create, read, update, delete collections and objects within them). - The [How-to: Query & Search](../how-to-query-search/index.md) guides show how to perform search operations (i.e. vector, keyword, hybrid) as well as retrieval augmented generation. ### References - OctoAI [API documentation](https://octo.ai/docs/getting-started/inference-models) Have a question or feedback? Here's how to reach us. ::::card-grid :::card{title="Community Forum" href="https://forum.weaviate.io/c/support" icon="messages-square"} Ask questions and connect with other developers on our **Community forum**. ::: :::card{title="Support" href="/guides/support-overview" icon="life-buoy"} Weaviate Cloud user or customer? Find the right channel on the **Support page**. ::: :::: ## Related pages - [Agents](./agents-index.md) - [AI-assisted Weaviate code generation](./ai-assisted-vibe-coding-index.md) - [APIs](./apis-index.md) - [Authorization and authentication](./authorization-and-authentication-index.md) - [Benchmarks](./benchmarks-index.md) - [Best practices](./best-practices-index.md) - [Client libraries](./clients-index.md) - [Client Libraries / SDKs](./client-libraries-index.md) - [Cloud](./cloud-index.md) - [Cloud account management](./cloud-account-management-index.md) # Agent Instructions This portal answers questions programmatically. To receive a synthesized, source-cited answer instead of crawling page by page, append the `?ask=` query parameter to any page URL on this site: /guides/quickstart?ask=how+do+I+authenticate Optional parameters: - `&goal=` steers the answer toward your objective (e.g. `&goal=write+a+python+client`). - `&version=