You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Welcome to the *Chat with your data* Solution accelerator repository! The *Chat with your data* Solution accelerator is a powerful tool that combines the capabilities of Azure AI Search and Large Language Models (LLMs) to create a conversational search experience. This solution accelerator uses an Azure OpenAI GPT model and an Azure AI Search index generated from your data, which is integrated into a web application to provide a natural language interface, including [speech-to-text](docs/speech_to_text.md) functionality, for search queries. Users can drag and drop files, point to storage, and take care of technical setup to transform documents. Everything can be deployed in your own subscription to accelerate your use of this technology.
50
50
51
-
51
+
52
+
52
53
53
54
### About this repo
54
55
@@ -91,12 +92,15 @@ Here is a comparison table with a few features offered by Azure, an available Gi
91
92
-**Single application access to your full data set**: Minimize endpoints required to access internal company knowledgebases. Reuse the same backend with the [Microsoft Teams Extension](docs/teams_extension.md)
92
93
-**Natural language interaction with your unstructured data**: Use natural language to quickly find the answers you need and ask follow-up queries to get the supplemental details, including [Speech-to-text](docs/speech_to_text.md).
93
94
-**Easy access to source documentation when querying**: Review referenced documents in the same chat window for additional context.
95
+
-**Chat history**: Prior conversations and context are maintained and accessible through chat history.
94
96
-**Data upload**: Batch upload documents of [various file types](docs/supported_file_types.md)
95
97
-**Accessible orchestration**: Prompt and document configuration (prompt engineering, document processing, and data retrieval)
98
+
-**Database flexibility**: Dynamic database switching allows users to choose between PostgreSQL and Cosmos DB based on their requirements. If no preference is specified the platform defaults to PostgreSQL.
96
99
97
100
98
101
**Note**: The current model allows users to ask questions about unstructured data, such as PDF, text, and docx files. See the [supported file types](docs/supported_file_types.md).
99
102
103
+
100
104
### Target end users
101
105
Company personnel (employees, executives) looking to research against internal unstructured company data would leverage this accelerator using natural language to find what they need quickly.
102
106
@@ -107,6 +111,11 @@ Tech administrators can use this accelerator to give their colleagues easy acces
107
111
108
112
### Use Case scenarios
109
113
114
+
#### Employee Onboarding Scenario
115
+
The sample data illustrates how this accelerator could be used for an employee onboarding scenario in across industries.
116
+
117
+
In this scenario, a newly hired employee is in the process of onboarding to their organization. Leveraging the solution accelerator, she navigates through the extensive offerings of her organization’s health and retirement benefits. With the newly integrated chat history capabilities, they can revisit previous conversations, ensuring continuity and context across multiple days of research. This functionality allows the new employee to efficiently gather and consolidate information, streamlining their onboarding experience. [For more details, refer to the README](docs/employee_assistance.md).
118
+
110
119
#### Financial Advisor Scenario
111
120
The sample data illustrates how this accelerator could be used in the financial services industry (FSI).
112
121
@@ -120,12 +129,6 @@ Additionally, we have implemented a Legal Review and Summarization Assistant sce
120
129
Note: Some of the sample data included with this accelerator was generated using AI and is for illustrative purposes only.
121
130
122
131
123
-
#### Employee Onboarding Scenario
124
-
The sample data illustrates how this accelerator could be used for an employee onboarding scenario in across industries.
125
-
126
-
In this scenario, a newly hired employee is in the process of onboarding to their organization. Leveraging the solution accelerator, she navigates through the extensive offerings of her organization’s health and retirement benefits. With the newly integrated chat history capabilities, they can revisit previous conversations, ensuring continuity and context across multiple days of research. This functionality allows the new employee to efficiently gather and consolidate information, streamlining their onboarding experience. [For more details, refer to the README](docs/employee_assistance.md).
@@ -146,6 +149,7 @@ In this scenario, a newly hired employee is in the process of onboarding to thei
146
149
- Azure Storage Account
147
150
- Azure Speech Service
148
151
- Azure CosmosDB
152
+
- Azure PostgreSQL
149
153
- Teams (optional: Teams extension only)
150
154
151
155
### Required licenses
@@ -163,13 +167,30 @@ The following are links to the pricing details for some of the resources:
163
167
-[Azure AI Document Intelligence pricing](https://azure.microsoft.com/pricing/details/ai-document-intelligence/)
164
168
-[Azure Web App Pricing](https://azure.microsoft.com/pricing/details/app-service/windows/)
165
169
170
+
### Deployment options: PostgreSQL or Cosmos DB
171
+
With the addition of PostgreSQL, customers can leverage the power of a relationship-based AI solution to enhance historical conversation access, improve data privacy, and open the possibilities for scalability.
172
+
173
+
Customers have the option to deploy this solution with PostgreSQL or Cosmos DB. Consider the following when deciding which database to use:
174
+
- PostgreSQL enables a relationship-based AI solution and search indexing for Retrieval Augmented Generation (RAG)
175
+
- Cosmos DB enables chat history and is a NoSQL-based solution. With Cosmos DB, Azure AI Search is used for storing extracted documents and embeddings.
176
+
177
+
178
+
To review PostgreSQL configuration overview and steps, follow the link [here](docs/postgreSQL.md).
179
+
180
+
181
+
To review Cosmos DB configuration overview and steps, follow the link [here](docs/employee_assistance.md).
182
+
183
+
166
184
### Deploy instructions
185
+
The "Deploy to Azure" button offers a one-click deployment where you don’t have to clone the code. If you would like a developer experience instead, follow the [local deployment instructions](./docs/LOCAL_DEPLOYMENT.md).
186
+
187
+
Once you deploy to Azure, you will have the option to select PostgreSQL or Cosmos DB, see screenshot below.
167
188
168
-
There are two choices; the "Deploy to Azure" offers a one click deployment where you don't have to clone the code, alternatively if you would like a developer experience, follow the [Local deployment instructions](./docs/LOCAL_DEPLOYMENT.md).
189
+
[](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2FAzure-Samples%2Fchat-with-your-data-solution-accelerator%2Frefs%2Fheads%2Fmain%2Finfra%2Fmain.json)
169
190
170
-
The demo, which uses containers pre-built from the main branch is available by clicking this button:
191
+
Select either "PostgreSQL" or "Cosmos DB":
192
+
171
193
172
-
[](https://portal.azure.com/#create/Microsoft.Template/uri/https%3A%2F%2Fraw.githubusercontent.com%2FAzure-Samples%2Fchat-with-your-data-solution-accelerator%2Fmain%2Finfra%2Fmain.json)
173
194
174
195
When Deployment is complete, follow steps in [Set Up Authentication in Azure App Service](./docs/azure_app_service_auth_setup.md) to add app authentication to your web app running on Azure App Service
175
196
@@ -195,9 +216,11 @@ switch to a lower version. To find out which versions are supported in different
195
216
196
217
0 commit comments