diff --git a/docs/configuration/memory.md b/docs/configuration/memory.md index 56d06b46b6..cfffe9c914 100644 --- a/docs/configuration/memory.md +++ b/docs/configuration/memory.md @@ -1,6 +1,6 @@ !!! warning - The Pinecone, Milvus and Weaviate memory backends were rendered incompatible - by work on the memory system, and have been removed in `master`. + The Pinecone, Milvus, Redis, and Weaviate memory backends were rendered incompatible + by work on the memory system, and have been removed. Whether support will be added back in the future is subject to discussion, feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280 @@ -18,6 +18,12 @@ to the value that you want: * `milvus` will use the milvus cache that you configured * `weaviate` will use the weaviate cache that you configured +!!! warning + The Pinecone, Milvus, Redis, and Weaviate memory backends were rendered incompatible + by work on the memory system, and have been removed. + Whether support will be added back in the future is subject to discussion, + feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280 + ## Memory Backend Setup Links to memory backends @@ -27,6 +33,12 @@ Links to memory backends - [Redis](https://redis.io) - [Weaviate](https://weaviate.io) +!!! warning + The Pinecone, Milvus, Redis, and Weaviate memory backends were rendered incompatible + by work on the memory system, and have been removed. + Whether support will be added back in the future is subject to discussion, + feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280 + ### Redis Setup !!! important @@ -62,6 +74,12 @@ Links to memory backends See [redis-stack-server](https://hub.docker.com/r/redis/redis-stack-server) for setting a password and additional configuration. +!!! warning + The Pinecone, Milvus, Redis, and Weaviate memory backends were rendered incompatible + by work on the memory system, and have been removed. + Whether support will be added back in the future is subject to discussion, + feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280 + ### 🌲 Pinecone API Key Setup Pinecone lets you store vast amounts of vector-based memory, allowing the agent to load only relevant memories at any given time. @@ -76,6 +94,12 @@ In the `.env` file set: - `PINECONE_ENV` (example: `us-east4-gcp`) - `MEMORY_BACKEND=pinecone` +!!! warning + The Pinecone, Milvus, Redis, and Weaviate memory backends were rendered incompatible + by work on the memory system, and have been removed. + Whether support will be added back in the future is subject to discussion, + feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280 + ### Milvus Setup [Milvus](https://milvus.io/) is an open-source, highly scalable vector database to store @@ -114,6 +138,12 @@ deployed with docker, or as a cloud service provided by [Zilliz Cloud](https://z - `MILVUS_COLLECTION` to change the collection name to use in Milvus. Defaults to `autogpt`. +!!! warning + The Pinecone, Milvus, Redis, and Weaviate memory backends were rendered incompatible + by work on the memory system, and have been removed. + Whether support will be added back in the future is subject to discussion, + feel free to pitch in: https://github.com/Significant-Gravitas/Auto-GPT/discussions/4280 + ### Weaviate Setup [Weaviate](https://weaviate.io/) is an open-source vector database. It allows to store data objects and vector embeddings from ML-models and scales seamlessly to billion of @@ -154,6 +184,15 @@ View memory usage by using the `--debug` flag :) ## 🧠 Memory pre-seeding + +!!! warning + Data ingestion is broken in v0.4.5 and possibly earlier versions. This is a known issue that will be addressed in future releases. Follow these issues for updates. + [Issue 4435](https://github.com/Significant-Gravitas/Auto-GPT/issues/4435) + [Issue 4024](https://github.com/Significant-Gravitas/Auto-GPT/issues/4024) + [Issue 2076](https://github.com/Significant-Gravitas/Auto-GPT/issues/2076) + + + Memory pre-seeding allows you to ingest files into memory and pre-seed it before running Auto-GPT. ``` shell