Add documentation for using Hugging Face models for embeddings (#549)

docs/endpoints.md

@@ -1,8 +1,6 @@
-### LLM Backends
-
 You can use MemGPT with various LLM backends, including the OpenAI API, Azure OpenAI, and various local (or self-hosted) LLM backends.
 
-#### OpenAI
+## OpenAI
 To use MemGPT with an OpenAI API key, simply set the `OPENAI_API_KEY` variable:
 ```sh
 export OPENAI_API_KEY=YOUR_API_KEY # on Linux/Mac
@@ -10,7 +8,11 @@ set OPENAI_API_KEY=YOUR_API_KEY # on Windows
 $Env:OPENAI_API_KEY = "YOUR_API_KEY" # on Windows (PowerShell)
 ```
 
-#### Azure
+#### OpenAI Proxies
+To use custom OpenAI endpoints, specify a proxy URL when running `memgpt configure` to set the custom endpoint as the default endpoint.
+
+
+## Azure
 To use MemGPT with Azure, expore the following variables and then re-run `memgpt configure`:
 ```sh
 # see https://github.com/openai/openai-python#microsoft-azure-endpoints
@@ -27,8 +29,5 @@ Replace `export` with `set` or `$Env:` if you are on Windows (see the OpenAI exa
 
 Note: **your Azure endpoint must support functions** or you will get an error. See [this GitHub issue](https://github.com/cpacker/MemGPT/issues/91) for more information.
 
-#### Custom endpoints
-To use custom OpenAI endpoints, run `export OPENAI_API_BASE=<MY_CUSTOM_URL>` and then re-run `memgpt configure` to set the custom endpoint as the default endpoint.
-
-#### Local LLMs
-Setting up MemGPT to run with local LLMs requires a bit more setup, follow [the instructions here](../local_llm).
+## Local Models & Custom Endpoints 
+MemGPT supports running open source models, both being run locally or as a hosted service. Setting up MemGPT to run with open models requires a bit more setup, follow [the instructions here](../local_llm).

docs/local_llm.md

@@ -99,6 +99,7 @@ Currently, MemGPT supports the following backends:
 * [LM Studio](../lmstudio) (Mac, Windows) (❌ does not support grammars)
 * [koboldcpp](../koboldcpp) (Mac, Windows, Linux) (✔️ supports grammars)
 * [llama.cpp](../llamacpp) (Mac, Windows, Linux) (✔️ supports grammars)
+* [vllm](../vllm) (Mac, Windows, Linux) (❌ does not support grammars)
 
 If you would like us to support a new backend, feel free to open an issue or pull request on [the MemGPT GitHub page](https://github.com/cpacker/MemGPT)!
 

docs/requirements.txt

@@ -3,3 +3,4 @@ furo
 myst-parser
 mkdocs
 mkdocs-material
+pymdown-extensions

mkdocs.yml

@@ -13,12 +13,13 @@ nav:
     - 'Example - chat with your data': example_data.md
     - 'Configuration': config.md
     - 'External data sources': data_sources.md
-    - 'Changing the LLM backend': endpoints.md
+    - 'Configuring LLMs': endpoints.md
+    - 'Configuring embeddings': embedding_endpoints.md
     - 'FAQ': cli_faq.md
   - 'Discord Bot':
     - 'Chatting with MemGPT Bot': discord_bot.md
-  - 'Local LLM':
-    - 'MemGPT + local LLMs': local_llm.md
+  - 'LLM Backends':
+    - 'MemGPT + open models': local_llm.md
     - 'oobabooga web UI': webui.md
     # - 'oobabooga web UI (on RunPod)': webui_runpod.md
     - 'LM Studio': lmstudio.md
@@ -37,7 +38,7 @@ nav:
     - 'Adding support for new LLMs': adding_wrappers.md
     - 'Contributing to the codebase': contributing.md
 theme:
-  name: material 
+  name: material
   features:
     - announce.dismiss
     - content.action.edit