# Generative search / RAG guide preview - feedback thread

**URL:** <https://forum.weaviate.io/t/generative-search-rag-guide-preview-feedback-thread/661>\
**Category:** Resources\
**Created:** [September 14, 2023, 7:30pm UTC](https://forum.weaviate.io/t/generative-search-rag-guide-preview-feedback-thread/661 "2023-09-14T19:30:42Z")\
**Posts on this page:** 7\
**Page:** 1

<div class="post-metadata">

**Author:** ![jphwang](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/jphwang/32/38_2.png) [@jphwang](https://forum.weaviate.io/u/jphwang)\
**Post date:** [September 14, 2023, 7:30pm UTC](https://forum.weaviate.io/t/generative-search-rag-guide-preview-feedback-thread/661/1 "2023-09-14T19:30:42Z")

</div>

Hi Weaviate friends,

We know that generative search, or RAG, is an important topic to many of you. So we have published a draft / preview of a guide for your feedback.

⬇ You can find it here ⬇

> **[Generative search (RAG) | Weaviate - vector database](https://weaviate.io/developers/weaviate/starter-guides/generative)**
>
> For now, the code examples are in Python only. Please be patient while we add code examples for other languages.

Please use this thread here to tell us what you think, as it will help us to help you. As a template, please let us know:

* * *

- What do you think overall (5: great, 1:not so much)?
- Is there anything missing that you want to know about?
- We only have Python examples here (yet - we wanted to get your feedback quickly 😉). We’ll add the others soon, but which language examples do you want to see most urgently?
- Any other comments?

* * *

---

<div class="post-metadata">

**Author:** ![ab19](https://avatars.discourse-cdn.com/v4/letter/a/47e85d/32.png) [@ab19](https://forum.weaviate.io/u/ab19)\
**Post date:** [September 15, 2023, 5:34am UTC](https://forum.weaviate.io/t/generative-search-rag-guide-preview-feedback-thread/661/2 "2023-09-15T05:34:10Z")

</div>

Looks awesome. Curious what settings are available in the LLM generation step? For example, temperature, system message, etc.

---

<div class="post-metadata">

**Author:** ![jphwang](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/jphwang/32/38_2.png) [@jphwang](https://forum.weaviate.io/u/jphwang)\
**Post date:** [September 15, 2023, 8:32am UTC](https://forum.weaviate.io/t/generative-search-rag-guide-preview-feedback-thread/661/3 "2023-09-15T08:32:08Z")

</div>

Hey @ab19 🙂

Thank you for writing with your feedback, and that is a great question!

Model properties are exposed through the Weaviate module configuration. So for example:

For `generative-cohere`:

```auto
        "generative-cohere": {
          "model": "command-xlarge-nightly", // Optional - Defaults to `command-xlarge-nightly`. Can also use`command-xlarge-beta` and `command-xlarge`
          "temperatureProperty": <temperature>, // Optional
          "maxTokensProperty": <maxTokens>, // Optional
          "kProperty": <k>, // Optional
          "stopSequencesProperty": <stopSequences>, // Optional
          "returnLikelihoodsProperty": <returnLikelihoods>, // Optional

```

For `generative-openai`:

```auto
        "generative-openai": {
          "model": "gpt-3.5-turbo", // Optional - Defaults to `gpt-3.5-turbo`
          "temperatureProperty": <temperature>, // Optional, applicable to both OpenAI and Azure OpenAI
          "maxTokensProperty": <max_tokens>, // Optional, applicable to both OpenAI and Azure OpenAI
          "frequencyPenaltyProperty": <frequency_penalty>, // Optional, applicable to both OpenAI and Azure OpenAI
          "presencePenaltyProperty": <presence_penalty>, // Optional, applicable to both OpenAI and Azure OpenAI
          "topPProperty": <top_p>, // Optional, applicable to both OpenAI and Azure OpenAI
        },

```

System messages are not customisable at the moment. I would ask you to [open an issue on GitHub](https://github.com/weaviate/weaviate/issues) if this is important to you. That’s because we do look at what the community votes on to prioritise feature development.

I will add this info in some capacity to the guide shortly.

---

<div class="post-metadata">

**Author:** ![KMohan](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/kmohan/32/551_2.png) [@KMohan](https://forum.weaviate.io/u/KMohan)\
**Post date:** [October 6, 2023, 10:26pm UTC](https://forum.weaviate.io/t/generative-search-rag-guide-preview-feedback-thread/661/4 "2023-10-06T22:26:07Z")

</div>

Love it! I already implemented CLI prototype for my domain data following your guide. I think “Create Class Definition” and “Import Data” section has the same piece of code. Also, where can I find all possible generative functions that are supported? I think you have used  
`grouped_task` and `single_prompt`. What other options are available?

---

<div class="post-metadata">

**Author:** ![jphwang](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/jphwang/32/38_2.png) [@jphwang](https://forum.weaviate.io/u/jphwang)\
**Post date:** [October 8, 2023, 1:20pm UTC](https://forum.weaviate.io/t/generative-search-rag-guide-preview-feedback-thread/661/5 "2023-10-08T13:20:16Z")

</div>

Hi @KMohan, at the moment these are the only two options. I know the team is definitely talking about extending these options.

If you would like to see, please file a request - it would help us to prioritize features if our users like yourself create these requests and upvote them 🙂

> **[Issues · weaviate/weaviate](https://github.com/weaviate/weaviate/issues)**
>
> Weaviate is an open source vector database that stores both objects and vectors, allowing for combining vector search with structured filtering with the fault-tolerance and scalability of a cloud-n...

---

<div class="post-metadata">

**Author:** ![KMohan](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/kmohan/32/551_2.png) [@KMohan](https://forum.weaviate.io/u/KMohan)\
**Post date:** [October 9, 2023, 8:29pm UTC](https://forum.weaviate.io/t/generative-search-rag-guide-preview-feedback-thread/661/6 "2023-10-09T20:29:40Z")

</div>

I may not be the right person because, I don’t know what other options are out there. I’m an app developer with no ML experience. I’m relying ML experts to educate us what is possible so I can go and build consumer facing apps using the technology.

---

<div class="post-metadata">

**Author:** ![jphwang](https://yyz1.discourse-cdn.com/flex027/user_avatar/forum.weaviate.io/jphwang/32/38_2.png) [@jphwang](https://forum.weaviate.io/u/jphwang)\
**Post date:** [October 16, 2023, 11:40am UTC](https://forum.weaviate.io/t/generative-search-rag-guide-preview-feedback-thread/661/7 "2023-10-16T11:40:14Z")

</div>

Yeah that’s fair.

We’ve definitely got more content coming up, and extending our RAG functionalities are in discussions too. Thanks @KMohan 🙂