Skip to content

Commit

Permalink
Update 6-chat-over-file.md
Browse files Browse the repository at this point in the history
  • Loading branch information
oliverlabs authored Aug 10, 2023
1 parent d4beffb commit 6a2c014
Showing 1 changed file with 6 additions and 6 deletions.
12 changes: 6 additions & 6 deletions docs/6-chat-over-file.md
Original file line number Diff line number Diff line change
Expand Up @@ -90,24 +90,24 @@ AZURE_SEARCH_INDEX_NAME=
AZURE_SEARCH_API_VERSION="2023-07-01-Preview"
```

3. Create Azure Document intelligence using the following [link](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/create-document-intelligence-resource?view=doc-intel-3.1.0)
3. Create an instance of Azure Form Recognizer (also known as Azure Document Intelligence) using the following [link](https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/create-document-intelligence-resource?view=doc-intel-3.1.0). Please be aware that this resource might be called 'Form recognizer' in Azure Portal.

4. After the Document intelligence has been created, proceed to modify the env.local file with the appropriate Document intelligence environment variables.
4. After the Form Recognizer (Document Intelligence) resource has been created, proceed to modify the `env.local` file with appropriate environment variables. You can find values for these variables in your _Form Recognizer_ resource (Resource Management blade > Keys and Endpoint). Please make sure that you don't copy the endpoint from there, but only replace the region in the example below. For example, if your Form Recognizer resource is located in East US Azure region, your `AZURE_DOCUMENT_INTELLIGENCE_ENDPOINT` variable would be `https://eastus.api.cognitive.microsoft.com/`.

Note that the file is only preserved for each chat thread
Please note that the file is only preserved for each chat thread:

```
# Azure AI Document Intelligence to extract content from your data
AZURE_DOCUMENT_INTELLIGENCE_ENDPOINT="https://REGION.api.cognitive.microsoft.com/"
AZURE_DOCUMENT_INTELLIGENCE_KEY=
```

4. At this point, you have the capability to generate a new chat session with opting for the `file chat` type. Click on the upload button to to start uploading a PDF file.
5. Upon the successful completion of the file upload, you are now able to commence the conversation using the provided text box.
4. At this point, you should have the capability to generate new chat sessions with opting of the `file chat` type. Click on the `Choose File` button to select your document and then the `Upload` button to upload your file. Please note that the Form Recognizer service supports PDF (text or scanned), JPG and PNG input documents.
6. Upon the successful completion of the file upload, you will be able to start a conversation with a chatbot using the chat box in the app.

### Things to consider:

1. Central place maintain uploaded files
1. Central place maintain uploaded files (e.g a storage account with blob storage)
2. A way to delete indexed documents on Azure Cognitive Search if the chat thread is deleted

[Next](/docs/7-environment-variables.md)

0 comments on commit 6a2c014

Please sign in to comment.