Docs: More ideas for improving search results (#1811)

* Add more customization ideas

* Add more customization ideas

Author: pamelafox

docs/customization.md

@@ -122,7 +122,7 @@ You can also try changing the ChatCompletion parameters, like temperature, to se
 
 ### Improving Azure AI Search results
 
-If the problem is with Azure AI Search (step 2 above), the first step is to check what search parameters you're using. Generally, the best results are found with hybrid search (text + vectors) plus the additional semantic re-ranking step, and that's what we've enabled by default. There may be some domains where that combination isn't optimal, however.
+If the problem is with Azure AI Search (step 2 above), the first step is to check what search parameters you're using. Generally, the best results are found with hybrid search (text + vectors) plus the additional semantic re-ranking step, and that's what we've enabled by default. There may be some domains where that combination isn't optimal, however. Check out this blog post which [evaluates AI search strategies](https://techcommunity.microsoft.com/t5/ai-azure-ai-services-blog/azure-ai-search-outperforming-vector-search-with-hybrid/ba-p/3929167) for a better understanding of the differences.
 
 #### Configuring parameters in the app
 
@@ -162,6 +162,15 @@ You can also use the `highlight` parameter to see what text is being matched in
 
 The search explorer works well for testing text, but is harder to use with vectors, since you'd also need to compute the vector embedding and send it in. It is probably easier to use the app frontend for testing vectors/hybrid search.
 
+#### Other approaches to improve search results
+
+Here are additional ways for improving the search results:
+
+- Adding additional metadata to the "content" field, like the document title, so that it can be matched in the search results. Modify [searchmanager.py](https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/app/backend/prepdocslib/searchmanager.py) to include more text in the `content` field.
+- Making additional fields searchable by the full text search step. For example, the "sourcepage" field is not currently searchable, but you could make that into a `SearchableField` with `searchable=True` in [searchmanager.py](https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/app/backend/prepdocslib/searchmanager.py). A change like that requires [re-building the index](https://learn.microsoft.com/azure/search/search-howto-reindex#change-an-index-schema).
+- Using function calling to search by particular fields, like searching by the filename. See this blog post on [function calling for structured retrieval](https://blog.pamelafox.org/2024/03/rag-techniques-using-function-calling.html).
+- Using a different splitting strategy for the documents, or modifying the existing ones, to improve the chunks that are indexed. You can find the currently available splitters in [textsplitter.py](https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/app/backend/prepdocslib/textsplitter.py).
+
 ### Evaluating answer quality
 
 Once you've made changes to the prompts or settings, you'll want to rigorously evaluate the results to see if they've improved. You can use tools in [the AI RAG Chat evaluator](https://github.com/Azure-Samples/ai-rag-chat-evaluator) repository to run evaluations, review results, and compare answers across runs.