Python: Autofunction calling is hallucinating the end result output for Semantic kernel Orchestrator Example for Python

[rakshahulle]

I have multiple plugins to invoke in sequence for Orchestration purposes. I have added all plugins to Kernel, I am using the automatic function calling to invoke a sequence of prompts for Orchestration flow. But the output for each time is hallucinating. I want to know how to give accurate prompts for Orchestration flow in Python.

[evchaki]

@rakshahulle - here are some samples - https://learn.microsoft.com/en-us/semantic-kernel/concepts/plugins/?pivots=programming-language-python

What model are you using?

[rakshahulle]

I am using Azure OpenAI GPT-4o Model

…

On Thu, Jan 2, 2025 at 9:55 PM EvanChaki_MSFT ***@***.***> wrote: @rakshahulle <https://github.com/rakshahulle> - here are some samples - https://learn.microsoft.com/en-us/semantic-kernel/concepts/plugins/?pivots=programming-language-python What model are you using? — Reply to this email directly, view it on GitHub <#10039 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AXCZPRLPJ3O26QPMJBLIGW32IVR67AVCNFSM6AAAAABUMF6A52VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNRYGAZTMNRTG4> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[evchaki]

@eavanvalkenburg / @moonbox3 fyi

[alliscode]

Hi @rakshahulle, if you are able to share your code and/or prompts then we might be able to provide some suggestions to reduce hallucinations. You can also take a look at some best practices for writing prompts: https://techcommunity.microsoft.com/blog/azure-ai-services-blog/15-tips-to-become-a-better-prompt-engineer-for-generative-ai/3882935

[rakshahulle]

Hi, I want to create one orchestration flow where the sequence is important. This is my prompt my use case: Cooking Recipe Recommendation System Step 1: Classify the image Classify the image into one of the following food categories: "Vegetarian" or "Non-Vegetarian." Step 2: Search Recipes According to the classification output, search for the top 10 {{$output}} recipes on Bing Web. Step 3: Retrieve Recipe Details For each recipe, retrieve the following details: - id: Recipe ID (unique identifier for the recipe) - name: Name of the recipe - ingredients: List of ingredients required - instructions: Step-by-step cooking instructions - url: URL of the recipe page - image_url: URL of the recipe image Step 4: Store Details into a Database Use a database table to store the recipe details with fields for id, name, ingredients, instructions, url, and image_url. Step 5: Show All Recipes from the Database Display all stored recipes from the database. Step 6: Display First Recipe Highlight the first recipe, showing its name, ingredients, instructions, and image_url.

…

On Thu, Jan 2, 2025 at 11:23 PM Ben Thomas ***@***.***> wrote: Hi @rakshahulle <https://github.com/rakshahulle>, if you are able to share your code and/or prompts then we might be able to provide some suggestions to reduce hallucinations. You can also take a look at some best practices for writing prompts: https://techcommunity.microsoft.com/blog/azure-ai-services-blog/15-tips-to-become-a-better-prompt-engineer-for-generative-ai/3882935 — Reply to this email directly, view it on GitHub <#10039 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AXCZPRLAGMQZX5IAH35DNMT2IV4H5AVCNFSM6AAAAABUMF6A52VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNRYGE2TAMBWGA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[rakshahulle]

These are some details. I want to use Automatic function calling for this use case. I have 3 plugins 1st is Bing web search, 2nd to retrieve details and store in id, name, instructions, URL, and image_url format, 3rd to store this in db, retrieve these details, display. On Fri, Jan 3, 2025 at 12:04 AM Raksha Hulle ***@***.***> wrote:

…

Hi, I want to create one orchestration flow where the sequence is important. This is my prompt my use case: Cooking Recipe Recommendation System Step 1: Classify the image Classify the image into one of the following food categories: "Vegetarian" or "Non-Vegetarian." Step 2: Search Recipes According to the classification output, search for the top 10 {{$output}} recipes on Bing Web. Step 3: Retrieve Recipe Details For each recipe, retrieve the following details: - id: Recipe ID (unique identifier for the recipe) - name: Name of the recipe - ingredients: List of ingredients required - instructions: Step-by-step cooking instructions - url: URL of the recipe page - image_url: URL of the recipe image Step 4: Store Details into a Database Use a database table to store the recipe details with fields for id, name, ingredients, instructions, url, and image_url. Step 5: Show All Recipes from the Database Display all stored recipes from the database. Step 6: Display First Recipe Highlight the first recipe, showing its name, ingredients, instructions, and image_url. On Thu, Jan 2, 2025 at 11:23 PM Ben Thomas ***@***.***> wrote: > Hi @rakshahulle <https://github.com/rakshahulle>, if you are able to > share your code and/or prompts then we might be able to provide some > suggestions to reduce hallucinations. You can also take a look at some best > practices for writing prompts: > https://techcommunity.microsoft.com/blog/azure-ai-services-blog/15-tips-to-become-a-better-prompt-engineer-for-generative-ai/3882935 > > — > Reply to this email directly, view it on GitHub > <#10039 (comment)>, > or unsubscribe > <https://github.com/notifications/unsubscribe-auth/AXCZPRLAGMQZX5IAH35DNMT2IV4H5AVCNFSM6AAAAABUMF6A52VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNRYGE2TAMBWGA> > . > You are receiving this because you were mentioned.Message ID: > ***@***.***> >