open source deployment section

content/20.results.md

@@ -24,7 +24,7 @@ In the following, we briefly describe these components, which are demonstrated i
 ### Question Answering and LLM Connectivity
 
 The core functionality of BioChatter is to interact with LLMs.
-The framework supports both leading proprietary models such as the GPT series from OpenAI as well as open-source models such as LLaMA2 [@doi:10.48550/arXiv.2307.09288] via a flexible open-source deployment framework [@{https://github.com/xorbitsai/inference}].
+The framework supports both leading proprietary models such as the GPT series from OpenAI as well as open-source models such as LLaMA2 [@doi:10.48550/arXiv.2307.09288] via a flexible open-source deployment framework [@{https://github.com/xorbitsai/inference}] (see Methods).
 Currently, the most powerful conversational AI platform, ChatGPT (OpenAI), is surrounded by data privacy concerns [@{https://www.reuters.com/technology/european-data-protection-board-discussing-ai-policy-thursday-meeting-2023-04-13/}].
 We address this issue in two ways.
 Firstly, we provide access to the different OpenAI models through their API, which is subject to different, more stringent data protection than the web interface [@{https://openai.com/policies/terms-of-use}], most importantly by disallowing reuse of user inputs for subsequent model training.

content/40.methods.md

@@ -66,6 +66,8 @@ This contextual information is transparently displayed in the main chat tab.
 Since this functionality requires a connection to a vector database system, we provide connectivity to a Milvus server, including a way to start the server in conjunction with a BioCypher knowledge graph and the ChatGSE app in one Docker Compose workflow.
 We plan to extend vector database support to several other standard vector database providers, such as Pinecone and Weaviate.
 
+### Deployment of Open-Source Models
+
 ### Model Chaining
 
 ### Remnants