Skip to content

Added ONNXEmbeddings for Chat with docs demo #1038

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
chetan-hirapara wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Added ONNXEmbeddings for Chat with docs demo #1038

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b65c73d
Replaced ivsm with onnx embeddings
chetan-hirapara Nov 18, 2025
13a904b
added step to verify audio model
chetan-hirapara Nov 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
146 changes: 73 additions & 73 deletions UseCases/Chat_with_docs_GenAI/Chat_with_docs_OpenSource_GenAI_Python.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

18 changes: 9 additions & 9 deletions UseCases/Chat_with_docs_GenAI/Chat_with_docs_VantageDB_GenAI_Python.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -603,19 +603,19 @@
"from IPython.display import display, Markdown\n",
"\n",
"def get_section5_desc_start():\n",
" return \"\"\"<p style = 'font-size:16px;font-family:Arial;color:#00233C'>The code above first reads the data from the files. The files contain information about the product embeddings and the customer's searched product embeddings. The code then loads the data into a permanent table in SQL. Once the data is loaded, we will use the Vantage in-database function <code>VectorDistance</code> to calculate the distance between the product embeddings and the customer's searched product embeddings. The data contains product embeddings, which are lists of numerical values, or vectors.</p>\n",
" <p style = 'font-size:16px;font-family:Arial;color:#00233C'>The embeddings file contains over 1500 records, each with 1,536 numerical features. This means that the file is quite large and it may take some time to load it into SQL.</p>\n",
" return \"\"\"<p style = 'font-size:16px;font-family:Arial'>The code above first reads the data from the files. The files contain information about the product embeddings and the customer's searched product embeddings. The code then loads the data into a permanent table in SQL. Once the data is loaded, we will use the Vantage in-database function <code>VectorDistance</code> to calculate the distance between the product embeddings and the customer's searched product embeddings. The data contains product embeddings, which are lists of numerical values, or vectors.</p>\n",
" <p style = 'font-size:16px;font-family:Arial'>The embeddings file contains over 1500 records, each with 1,536 numerical features. This means that the file is quite large and it may take some time to load it into SQL.</p>\n",
" <div class=\"alert alert-block alert-info\" id=\"no-azure\">\n",
" <p style = 'font-size:16px;font-family:Arial;color:#00233C'><i><b>Note</b>: Please be patient. The code above is loading data from files and copying it to SQL. This process may take 30-50 seconds.</i></p>\n",
" <p style = 'font-size:16px;font-family:Arial'><i><b>Note</b>: Please be patient. The code above is loading data from files and copying it to SQL. This process may take 30-50 seconds.</i></p>\n",
" </div>\"\"\"\n",
"\n",
"def get_section5_desc_end():\n",
" return \"\"\"<a id='section52'></a><p style = 'font-size:18px;font-family:Arial;color:#00233c'><b>5.2 Display the product embeddings</b></p>\n",
" <p style = 'font-size:16px;font-family:Arial;color:#00233C'>To give you a better idea of what the embeddings look like, here are the first five rows of the product embeddings:</p>\"\"\"\n",
" return \"\"\"<a id='section52'></a><p style = 'font-size:18px;font-family:Arial'><b>5.2 Display the product embeddings</b></p>\n",
" <p style = 'font-size:16px;font-family:Arial'>To give you a better idea of what the embeddings look like, here are the first five rows of the product embeddings:</p>\"\"\"\n",
"\n",
"def get_section5_desc_sample():\n",
" return \"\"\"<p style = 'font-size:16px;font-family:Arial;color:#00233C'>We can see that generated embeddings for all of the products are in vector of 1536 columns. </p>\n",
" <p style = 'font-size:16px;font-family:Arial;color:#00233C'>For example: The generated embeddings for product name: <b>What is the email address of Customer Service Department?</b> consists of 1536 numbers and looks like:<br>\n",
" return \"\"\"<p style = 'font-size:16px;font-family:Arial'>We can see that generated embeddings for all of the products are in vector of 1536 columns. </p>\n",
" <p style = 'font-size:16px;font-family:Arial'>For example: The generated embeddings for product name: <b>What is the email address of Customer Service Department?</b> consists of 1536 numbers and looks like:<br>\n",
" <code>-0.038744\t-0.016937\t-0.017475\t0.003624\t0.00744\t-0.00275\t0.02374</code></p>\"\"\"\n",
"\n",
"def load_the_emb():\n",
Expand Down Expand Up @@ -649,7 +649,7 @@
" display(\n",
" Markdown(\n",
" \"\"\"<br><div class=\"alert alert-block alert-success\">\n",
" <p style = 'font-size:16px;font-family:Arial;color:#00233C'><i>Section 4: Generate the embeddings is already executed! So, skipping the execution of above code.</i></p></div>\"\"\"\n",
" <p style = 'font-size:16px;font-family:Arial'><i>Section 4: Generate the embeddings is already executed! So, skipping the execution of above code.</i></p></div>\"\"\"\n",
" )\n",
" )\n",
"\n",
Expand Down Expand Up @@ -1143,7 +1143,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.10"
"version": "3.11.14"
}
},
"nbformat": 4,
Expand Down
Loading
Loading