Embedchain also provides support for creating Open-Source AI Assistants (similar to OpenAI Assistants API) which allows you to build AI assistants within your own applications using any LLM (OpenAI or otherwise). An Assistant has instructions and can leverage models, tools, and knowledge to respond to user queries.

At a high level, the Open-Source AI Assistants API has the following flow:

  1. Create an AI Assistant by picking a model
  2. Create a Thread when a user starts a conversation
  3. Add Messages to the Thread as the user ask questions
  4. Run the Assistant on the Thread to trigger responses. This automatically calls the relevant tools.

Creating an Open-Source AI Assistant is a simple 3 step process.

​
Step 1: Instantiate AI Assistant

Initialize
from embedchain.store.assistants import AIAssistant

assistant = AIAssistant(
    name="My Assistant",
    data_sources=[{"source": "https://www.youtube.com/watch?v=U9mJuUkhUzk"}])

If you want to use the existing assistant, you can do something like this:

Initialize
# Load an assistant and create a new thread
assistant = AIAssistant(assistant_id="asst_xxx")

# Load a specific thread for an assistant
assistant = AIAssistant(assistant_id="asst_xxx", thread_id="thread_xxx")

​
Step-2: Add data to thread

You can add any custom data source that is supported by Embedchain. Else, you can directly pass the file path on your local system and Embedchain propagates it to OpenAI Assistant.

Add data
assistant.add("/path/to/file.pdf")
assistant.add("https://www.youtube.com/watch?v=U9mJuUkhUzk")
assistant.add("https://openai.com/blog/new-models-and-developer-products-announced-at-devday")

​
Step-3: Chat with your AI Assistant

Chat
assistant.chat("How much OpenAI credits were offered to attendees during OpenAI DevDay?")
# Response: 'Every attendee of OpenAI DevDay 2023 was offered $500 in OpenAI credits.'