Yes, you absolutely can, and it's generally recommended for getting the best context and generative answers from Vertex AI Search when dealing with software projects.
The key is to consider how Vertex AI Search (and the underlying LLM) will interpret the relationship between your source code and its accompanying documentation.
Here are the main strategies, from simplest to most effective:
| Origin: Bluekiri Demo | |
| Label: bluekiri | |
| Codename: bionic | |
| Architectures: amd64 | |
| Components: main | |
| Description: Personal repository | |
| SignWith: B501DE17DA19A16F |
| [Unit] | |
| Description=Demo Api Service | |
| After=network.target | |
| [Service] | |
| Type=simple | |
| ExecStart=/opt/bluekiri/demoapi/demoapi | |
| ExecReload=/bin/kill -HUP $MAINPID | |
| [Install] |
| #!/usr/bin/make -f | |
| #export DH_VERBOSE = 1 | |
| %: | |
| dh $@ --with=systemd | |
| override_dh_auto_build: | |
| dotnet publish -c Release --self-contained -r ubuntu.18.04-x64 | |
| # auto-build disabled |
| Source: demoapi | |
| Section: net | |
| Priority: optional | |
| Maintainer: Bluekiri Demo <[email protected]> | |
| Build-Depends: debhelper (>= 10), dh-systemd | |
| Standards-Version: 4.1.2 | |
| Homepage: https://github.com/bluekiri/demoapi | |
| Package: demoapi | |
| Architecture: any |
| demoapi (1.0-0ubuntu1) bionic; urgency=medium | |
| * Initial Release. | |
| -- Bluekiri Demo <[email protected]> Tue, 13 Nov 2018 08:23:08 +0000 |
| <Project Sdk="Microsoft.NET.Sdk.Web"> | |
| <PropertyGroup> | |
| <TargetFramework>netcoreapp2.1</TargetFramework> | |
| <RuntimeIdentifiers>ubuntu.18.04-x64</RuntimeIdentifiers> | |
| </PropertyGroup> | |
| <ItemGroup> | |
| <Folder Include="wwwroot\" /> | |
| </ItemGroup> |
| import numpy as np | |
| from statsmodels.tsa.tsatools import lagmat | |
| def johansen(ts, lags): | |
| """ | |
| Calculate the Johansen Test for the given time series | |
| """ | |
| # Make sure we are working with arrays, convert if necessary | |
| ts = np.asarray(ts) |
| import numpy as np | |
| from statsmodels.regression.linear_model import OLS | |
| from statsmodels.tsa.tsatools import lagmat, add_trend | |
| from statsmodels.tsa.adfvalues import mackinnonp | |
| def adf(ts, maxlag=1): | |
| """ | |
| Augmented Dickey-Fuller unit root test | |
| """ | |
| # make sure we are working with an array, convert if necessary |
| import numpy as np | |
| def half_life(ts): | |
| """ | |
| Calculates the half life of a mean reversion | |
| """ | |
| # make sure we are working with an array, convert if necessary | |
| ts = np.asarray(ts) | |
| # delta = p(t) - p(t-1) |