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
Copy file name to clipboardExpand all lines: docs/LOCAL_DEPLOYMENT.md
+4-1Lines changed: 4 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -192,8 +192,11 @@ Execute the above [shell command](#L81) to run the function locally. You may nee
192
192
|AZURE_OPENAI_RESOURCE||the name of your Azure OpenAI resource|
193
193
|AZURE_OPENAI_MODEL||The name of your model deployment|
194
194
|AZURE_OPENAI_MODEL_NAME|gpt-35-turbo|The name of the model|
195
+
|AZURE_OPENAI_MODEL_VERSION|0613|The version of the model to use|
195
196
|AZURE_OPENAI_API_KEY||One of the API keys of your Azure OpenAI resource|
196
-
|AZURE_OPENAI_EMBEDDING_MODEL|text-embedding-ada-002|The name of you Azure OpenAI embeddings model deployment|
197
+
|AZURE_OPENAI_EMBEDDING_MODEL|text-embedding-ada-002|The name of your Azure OpenAI embeddings model deployment|
198
+
|AZURE_OPENAI_EMBEDDING_MODEL_NAME|text-embedding-ada-002|The name of the embeddings model (can be found in Azure AI Studio)|
199
+
|AZURE_OPENAI_EMBEDDING_MODEL_VERSION|2|The version of the embeddings model to use (can be found in Azure AI Studio)|
197
200
|AZURE_OPENAI_TEMPERATURE|0|What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. A value of 0 is recommended when using your data.|
198
201
|AZURE_OPENAI_TOP_P|1.0|An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. We recommend setting this to 1.0 when using your data.|
199
202
|AZURE_OPENAI_MAX_TOKENS|1000|The maximum number of tokens allowed for the generated answer.|
[Back to *Chat with your data* README](../README.md)
2
+
3
+
# Overview
4
+
5
+
This document outlines the necessary steps and configurations required for setting up and using models within the solution. It serves as a guide for developers to configure and customize model settings according to the project's needs.
6
+
7
+
# Model Selection
8
+
9
+
## Available Models
10
+
11
+
- For a list of available models, see the [Microsoft Azure AI Services - OpenAI Models documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models).
12
+
13
+
## Environment Variables (as listed in Azure AI Studio)
14
+
- You can access the Environment Variables section of the `LOCAL_DEPLOYMENT.md` file by clicking on this link: [Environment Variables section in LOCAL_DEPLOYMENT.md](docs/LOCAL_DEPLOYMENT.md#environment-variables).
15
+
16
+
### LLM
17
+
-`AZURE_OPENAI_MODEL`: The Azure OpenAI Model Deployment Name
18
+
- example: `my-gpt-35-turbo-16k`
19
+
-`AZURE_OPENAI_MODEL_NAME`: The Azure OpenAI Model Name
20
+
- example: `gpt-35-turbo-16k`
21
+
-`AZURE_OPENAI_MODEL_VERSION`: The Azure OpenAI Model Version
22
+
- example: `0613`
23
+
-`AZURE_OPENAI_MODEL_CAPACITY`: The Tokens per Minute Rate Limit (thousands)
24
+
- example: `30`
25
+
26
+
### VISION
27
+
-`AZURE_OPENAI_VISION_MODEL`: The Azure OpenAI Model Deployment Name
28
+
- example: `my-gpt-4`
29
+
-`AZURE_OPENAI_VISION_MODEL_NAME`: The Azure OpenAI Model Name
30
+
- example: `gpt-4`
31
+
-`AZURE_OPENAI_VISION_MODEL_VERSION`: The Azure OpenAI Model Version
32
+
- example: `vision-preview`
33
+
-`AZURE_OPENAI_VISION_MODEL_CAPACITY`: The Tokens per Minute Rate Limit (thousands)
34
+
- example: `10`
35
+
36
+
### EMBEDDINGS
37
+
-`AZURE_OPENAI_EMBEDDING_MODEL`: The Azure OpenAI Model Deployment Name
38
+
- example: `my-text-embedding-ada-002`
39
+
-`AZURE_OPENAI_EMBEDDING_MODEL_NAME`: The Azure OpenAI Model Name
40
+
- example: `text-embedding-ada-002`
41
+
-`AZURE_OPENAI_EMBEDDING_MODEL_VERSION`: The Azure OpenAI Model Version
42
+
- example: `2`
43
+
-`AZURE_OPENAI_EMBEDDING_MODEL_CAPACITY`: The Tokens per Minute Rate Limit (thousands)
44
+
- example: `30`
45
+
-`AZURE_SEARCH_DIMENSIONS`: Azure OpenAI Embeddings dimensions. A full list of dimensions can be found [here](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models#embeddings-models).
46
+
- example: `1536`
47
+
48
+
### OPENAI API Configuration
49
+
-`AZURE_OPENAI_API_VERSION`: The Azure OpenAI API Version
50
+
- example: `2024-02-01`
51
+
-`AZURE_OPENAI_MAX_TOKENS`: The Maximum Tokens per Request
52
+
- example: `1000`
53
+
-`AZURE_OPENAI_TEMPERATURE`: The Sampling Temperature (from 0 to 1)
54
+
- example: `0`
55
+
-`AZURE_OPENAI_TOP_P`: The Top P Sampling Probability
56
+
- example: `1`
57
+
58
+
# Model Configuration
59
+
- To set an environment variable, you can use the following command:
60
+
-`azd env set <ENVIRONMENT_VARIABLE_NAME> <ENVIRONMENT_VARIABLE_VALUE>`
61
+
62
+
- To get the value of an environment variable, you can use the following command:
63
+
-`azd env get <ENVIRONMENT_VARIABLE_NAME>`
64
+
65
+
## GPT-4o & Text-Embeddings-3-Large
66
+
- The following environment variables are set for the GPT-4o and Text-Embeddings-3-Large models:
0 commit comments