-
Notifications
You must be signed in to change notification settings - Fork 4.5k
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.
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
L starryskyl patch 1 #2359
L starryskyl patch 1 #2359
Conversation
@microsoft-github-policy-service agree |
@microsoft-github-policy-service agree |
This looks like an unintentional PR? |
Hello Pamela ،
Actually this is my first project so I may I done this but mistake however
I do need help on how to use deepseek along with a rag pipeline I'd
appreciate any help you can offer.
Regards,
Omar
…On Fri, 14 Feb 2025, 4:04 am Pamela Fox, ***@***.***> wrote:
This looks like an unintentional PR?
Closing.
Let me know if you need help using DeepSeek with the repo. I haven't done
it, but I have used it outside the repo.
—
Reply to this email directly, view it on GitHub
<#2359 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/A2GTODKFH3CKZGJKRN734A32PU6LTAVCNFSM6AAAAABXCXJZ4CVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMNJYGAZTAOJQGI>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
[image: pamelafox]*pamelafox* left a comment
(Azure-Samples/azure-search-openai-demo#2359)
<#2359 (comment)>
This looks like an unintentional PR?
Closing.
Let me know if you need help using DeepSeek with the repo. I haven't done
it, but I have used it outside the repo.
—
Reply to this email directly, view it on GitHub
<#2359 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/A2GTODKFH3CKZGJKRN734A32PU6LTAVCNFSM6AAAAABXCXJZ4CVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMNJYGAZTAOJQGI>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
Okay, please open an issue in the issue tracker about DeepSeek usage. I haven't tried it in this repo yet, but a short answer is:
client = AzureOpenAI(
result = client.chat.completions.create(
I have weekly office hours as well, if you want to ask there: |
Thanks, I'll check it out. I have other questions I'll visit your office
hours.
…On Fri, 14 Feb 2025, 10:17 am Pamela Fox, ***@***.***> wrote:
Okay, please open an issue in the issue tracker about DeepSeek usage.
I haven't tried it in this repo yet, but a short answer is:
1.
Deploy DeepSeek to Azure AI Services. You can use the Bicep here or do
it from the Portal:
https://github.com/Azure-Samples/deepseek-python
2.
Modify the AzureOpenAI constructor to pass in the correct base
endpoint:
client = AzureOpenAI(
api_version=os.environ["AZURE_INFERENCE_API_VERSION"],
base_url=os.environ["AZURE_INFERENCE_ENDPOINT"],
azure_ad_token_provider=token_provider,
)
3. Modify the chat completion call to pass the model in this way:
result = client.chat.completions.create(
# This *must* be None, even though it technically is meant to be a str,
# because thats the only way to get the AzureOpenAI class to skip the
addition of 'deployments/model' to the URL:
model=None,
# We must pass the model in the header, since we need to pass model=None
to create
extra_headers={"x-ms-model-mesh-model-name": "DeepSeek-R1"},
..
4. And then you'll need to decide how you want to handle the think
block. See my repo above or my blog post here:
https://blog.pamelafox.org/2025/01/observations-using-python-with-deepseek.html
I have weekly office hours as well, if you want to ask there:
http://aka.ms/aipython/oh
—
Reply to this email directly, view it on GitHub
<#2359 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/A2GTODOTTVMUPO7N2GIYQQT2PWKAPAVCNFSM6AAAAABXCXJZ4CVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMNJYGQ3DKOJTGY>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
[image: pamelafox]*pamelafox* left a comment
(Azure-Samples/azure-search-openai-demo#2359)
<#2359 (comment)>
Okay, please open an issue in the issue tracker about DeepSeek usage.
I haven't tried it in this repo yet, but a short answer is:
1.
Deploy DeepSeek to Azure AI Services. You can use the Bicep here or do
it from the Portal:
https://github.com/Azure-Samples/deepseek-python
2.
Modify the AzureOpenAI constructor to pass in the correct base
endpoint:
client = AzureOpenAI(
api_version=os.environ["AZURE_INFERENCE_API_VERSION"],
base_url=os.environ["AZURE_INFERENCE_ENDPOINT"],
azure_ad_token_provider=token_provider,
)
3. Modify the chat completion call to pass the model in this way:
result = client.chat.completions.create(
# This *must* be None, even though it technically is meant to be a str,
# because thats the only way to get the AzureOpenAI class to skip the
addition of 'deployments/model' to the URL:
model=None,
# We must pass the model in the header, since we need to pass model=None
to create
extra_headers={"x-ms-model-mesh-model-name": "DeepSeek-R1"},
..
4. And then you'll need to decide how you want to handle the think
block. See my repo above or my blog post here:
https://blog.pamelafox.org/2025/01/observations-using-python-with-deepseek.html
I have weekly office hours as well, if you want to ask there:
http://aka.ms/aipython/oh
—
Reply to this email directly, view it on GitHub
<#2359 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/A2GTODOTTVMUPO7N2GIYQQT2PWKAPAVCNFSM6AAAAABXCXJZ4CVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMNJYGQ3DKOJTGY>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
Purpose
Does this introduce a breaking change?
When developers merge from main and run the server, azd up, or azd deploy, will this produce an error?
If you're not sure, try it out on an old environment.
Does this require changes to learn.microsoft.com docs?
This repository is referenced by this tutorial
which includes deployment, settings and usage instructions. If text or screenshot need to change in the tutorial,
check the box below and notify the tutorial author. A Microsoft employee can do this for you if you're an external contributor.
Type of change
Code quality checklist
See CONTRIBUTING.md for more details.
python -m pytest
).python -m pytest --cov
to verify 100% coverage of added linespython -m mypy
to check for type errorsruff
andblack
manually on my code.