nl2sql tool for prompt flow
How to create promptflow endpoint your workspace
1. Prepare your workspace
Open your workspace in Azure ML studio portal
Example Studio Portal URL:
https://main.ml.azure.com/?wsid=/subscriptions/1b75927d-563b-49d2-bf8a-772f7d6a170e/resourceGroups/ragdev/providers/Microsoft.MachineLearningServices/workspaces/RAGDev&flight=promptDesigner&tid=72f988bf-86f1-41af-91ab-2d7cd011db47
2. Create a ci (compute instance)
Create a ci with name with prefix "ci-lin-cpu-0-" , for example ci-lin-cpu-0-alan
3. Config Customer Application on your ci
3.1 Application Name
Application Name has to be: promptflow-runtime
3.2 Port
Target Port and Published Port have to be: 8080
3.3 Docker Image
docker image can be modulesdkpreview/prt:tag.
For example:
modulesdkpreview/prt:v20230420-140738
3.4 Restart ci
4. Install dbcopilot on your ci
4.1 Open Terminal of your ci
4.2 upload whl files to your ci
dbcopilot-0.2.0-py3-none-any.whl (get it from https://dev.azure.com/TScience/NL2Code/_artifacts/feed/AIMS.TScience.NL2Code/PyPI/dbcopilot/overview/0.3.0)
db_copilot_tool-0.1.0-py3-none-any.whl
embeddingstore-0.0.1-py3-none-any.whl (optional)
promptflow_sdk-0.0.1-py3-none-any.whl (optional)
4.3 Install whl files in promptflow container
Find your promptflow container id with command: docker ps -a
Copy whl files to promptflow container with command: docker cp xxx.whl <container_id>:/xxx.whl
Login promptflow container with command: docker exec -it <container_id> /bin/bash
install whl files with command: pip install xxx.whl
4.4 Install Microsoft ODBC in promptflow container
Reference Doc: https://learn.microsoft.com/en-us/sql/connect/odbc/linux-mac/installing-the-microsoft-odbc-driver-for-sql-server?view=sql-server-ver16&tabs=ubuntu18-install%2Calpine17-install%2Cdebian8-install%2Credhat7-13-install%2Crhel7-offline#18
Commands:
apt-get update
apt-get install -y curl lsb-core
curl https://packages.microsoft.com/keys/microsoft.asc | apt-key add -
curl https://packages.microsoft.com/config/ubuntu/$(lsb_release -rs)/prod.list > /etc/apt/sources.list.d/mssql-release.list
apt-get update
ACCEPT_EULA=Y apt-get install -y msodbcsql18
apt-get install -y unixodbc-dev
4.5 Restart promptflow container
exit
docker stop container_id
docker start container_id
5. Copy Local DB file to promptflow container (optional)
6. Get promptflow endpoint url
promptflow endpoint url can be found in the ci overview page, click "promptflow-runtime" link
Metadata
Release files for db-copilot-tool 0.0.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| db_copilot_tool-0.0.8.tar.gz | 1.3 MB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| db_copilot_tool-0.0.8-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.7 MB
Release files / db_copilot_tool-0.0.8.tar.gz
| Download URL | db_copilot_tool-0.0.8.tar.gz |
|---|---|
| Size | 1.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
ecd0d5fe6bdd100bf9ab83fcb8fe53a8afd4a08344c3a43d77be75eb9e3182b0
|
|
BLAKE2b-256 checksum How to use checksums |
84f3cb926a43cbbb958fa601d4bbe0ee35274111fbeff25574408160ae690dd6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.11.5
|
Release files / db_copilot_tool-0.0.8-py3-none-any.whl
| Download URL | db_copilot_tool-0.0.8-py3-none-any.whl |
|---|---|
| Size | 1.4 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
42085f71a3f52cb30added0014a31302477c96082404bf8886e0b2dace66dc65
|
|
BLAKE2b-256 checksum How to use checksums |
a5bbfa034361e512e8244e402bb1155c56a0f9a5d6aa174696e2a0d0ded726fd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.11.5
|
Security for db-copilot-tool 0.0.8
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.