# New Assistant feature and Fine-tuning **URL:** \ **Category:** API\ **Created:** [November 8, 2023, 1:33am UTC](https://community.openai.com/t/new-assistant-feature-and-fine-tuning/480721 "2023-11-08T01:33:54Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![cramtek](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/cramtek/32/511473_2.png) [@cramtek](https://community.openai.com/u/cramtek)\ **Post date:** [November 8, 2023, 1:33am UTC](https://community.openai.com/t/new-assistant-feature-and-fine-tuning/480721/1 "2023-11-08T01:33:54Z")
Hello! I’ve been exploring the newly launched Assistants features and I’m curious if the context provided for each Assistant is similar to fine-tuned training for specific entities. Can an Assistant also incorporate fine-tuning files or training, or are they mutually exclusive? Could someone clarify this for me, please? ---
**Author:** ![Daan.minimum](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/daan.minimum/32/33117_2.png) [@Daan.minimum](https://community.openai.com/u/Daan.minimum)\ **Post date:** [November 9, 2023, 4:51am UTC](https://community.openai.com/t/new-assistant-feature-and-fine-tuning/480721/2 "2023-11-09T04:51:17Z")
Following this thread! Would be interesting to get more info on how assistants (with context and files) compare to a finetuned model. Seems like assistants might be a better way to go since they allow for multiple tools to use! ---
**Author:** ![christian11](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/christian11/32/248871_2.png) [@christian11](https://community.openai.com/u/christian11)\ **Post date:** [November 14, 2023, 11:03pm UTC](https://community.openai.com/t/new-assistant-feature-and-fine-tuning/480721/3 "2023-11-14T23:03:40Z")
+1 I just setup a support agent assistant to read my knowledge base. Its really close to being accurate - and I feel like if there was a tuning option it could get there quicker. Right now, I’d have to rewrite many articles to make them more AI friendly at the expense of being less clear to humans ---
**Author:** ![andrea.tomassi](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/andrea.tomassi/32/290748_2.png) [@andrea.tomassi](https://community.openai.com/u/andrea.tomassi)\ **Post date:** [January 20, 2024, 11:02am UTC](https://community.openai.com/t/new-assistant-feature-and-fine-tuning/480721/4 "2024-01-20T11:02:49Z")
+1 This feature enables the setup of an assistant with file retrieval AND a finely tuned model to generate the answer. Often, the documentation from OpenAI itself explains that fine-tuning and data-retrieval are complementary approaches. However, I still can’t see how I can leverage both of them in the same Assistant. ---
**Author:** ![bludodo](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/bludodo/32/300538_2.png) [@bludodo](https://community.openai.com/u/bludodo)\ **Post date:** [February 5, 2024, 7:36am UTC](https://community.openai.com/t/new-assistant-feature-and-fine-tuning/480721/5 "2024-02-05T07:36:19Z")
I’ll try to do the code now i don think it could hurt to much in the pockets if the systems are complementary. The solution i would implement is to have three open ai assistants, one make function calls to to: - generate model training data - validate the training data - create the model To create assistants - [https://platform.openai.com/docs/assistants/overview](https://platform.openai.com/docs/assistants/overview) I’ll go read up on fine-tuning now [https://platform.openai.com/docs/api-reference/fine-tuning/create](https://platform.openai.com/docs/api-reference/fine-tuning/create) P.s Im tapping out early. Seems to be for commercial use. It says we need samples of a minimum of 50-100 high quality examples to train the model in batches. It suggests focusing on getting good at prompt completions, which i don’t have yet, that will translate into the example data for training a model. I figure when i get 200-300 specific prompts I’ll give it a go