diff --git a/qdrant-landing/content/documentation/frameworks/_index.md b/qdrant-landing/content/documentation/frameworks/_index.md index 4357b5098..dd87ef630 100644 --- a/qdrant-landing/content/documentation/frameworks/_index.md +++ b/qdrant-landing/content/documentation/frameworks/_index.md @@ -23,9 +23,10 @@ weight: 33 | [Langchain4j](./langchain4j/) | Java framework for building context-aware, reasoning applications using LLMs. | | [LlamaIndex](./llama-index/) | A data framework for building LLM applications with modular integrations. | | [Make](./make/) | Cloud platform to build low-code workflows by integrating various software applications. | +| [MemGPT](./memgpt/) | System to build LLM agents with long term memory & custom tools | | [MindsDB](./mindsdb/) | Platform to deploy, serve, and fine-tune models with numerous data source integrations. | | [N8N](./n8n/) | Platform for node-based, low-code workflow automation. | -| [OpenLIT](./openlit/) | OpenTelemetry-native Observability & Evals for LLMs and Vector Databases. | +| [OpenLIT](./openlit/) | Platform for OpenTelemetry-native Observability & Evals for LLMs and Vector Databases. | | [OpenLLMetry](./openllmetry/) | Set of OpenTelemetry extensions to add Observability for your LLM application. | | [Pandas-AI](./pandas-ai/) | Python library to query/visualize your data (CSV, XLSX, PostgreSQL, etc.) in natural language | | [Pipedream](./pipedream/) | Platform for connecting apps and developing event-driven automations. | diff --git a/qdrant-landing/content/documentation/frameworks/memgpt.md b/qdrant-landing/content/documentation/frameworks/memgpt.md new file mode 100644 index 000000000..a94f687a8 --- /dev/null +++ b/qdrant-landing/content/documentation/frameworks/memgpt.md @@ -0,0 +1,52 @@ +--- +title: MemGPT +weight: 3200 +--- + +# MemGPT + +[MemGPT](https://memgpt.ai/) is a system that enables LLMs to manage their own memory and overcome limited context windows to + +- Create perpetual chatbots that learn about you and change their personalities over time. +- Create perpetual chatbots that can interface with large data stores. + +Qdrant is available as a storage backend in MemGPT for storing and semantically retrieving data. + +## Usage + +#### Installation + +To install the required dependencies, install `pymemgpt` with the `qdrant` extra. + +```sh +pip install 'pymemgpt[qdrant]' +``` + +You can configure MemGPT to use either a Qdrant server or an in-memory instance with the `memgpt configure` command. + +#### Configuring the Qdrant server + +When you run `memgpt configure`, go through the prompts as described in the [MemGPT configuration documentation](https://memgpt.readme.io/docs/config). +After you address several `memgpt` questions, you come to the following `memgpt` prompts: + +```console +? Select storage backend for archival data: qdrant +? Select Qdrant backend: server +? Enter the Qdrant instance URI (Default: localhost:6333): https://xyz-example.eu-central.aws.cloud.qdrant.io +``` + +You can set an API key for authentication using the `QDRANT_API_KEY` environment variable. + +#### Configuring an in-memory instance + +```console +? Select storage backend for archival data: qdrant +? Select Qdrant backend: local +``` + +The data is persisted at the default MemGPT storage directory. + +## Further Reading + +- [MemGPT Examples][https://github.com/cpacker/MemGPT/tree/main/examples] +- [MemGPT Documentation](https://memgpt.readme.io/docs/index). diff --git a/qdrant-landing/static/documentation/frameworks/memgpt-social-preview.png b/qdrant-landing/static/documentation/frameworks/memgpt-social-preview.png new file mode 100644 index 000000000..5adb23598 Binary files /dev/null and b/qdrant-landing/static/documentation/frameworks/memgpt-social-preview.png differ