klas/t6_mem0
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[Docs] Add docs for Azure OpenAI provider (#804)

Browse Source
This commit is contained in:
Deshraj Yadav
2023-10-16 13:31:56 -07:00
committed by GitHub
parent 636bc0a99d
commit adf50f1e81
7 changed files with 299 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
.gitignore vendored
View File

@@ -76,7 +76,7 @@ docs/_build/
target/
# Jupyter Notebook
.ipynb_checkpoints
*.yaml
# IPython
profile_default/
@@ -171,3 +171,6 @@ db
.idea/
.DS_Store
notebooks/*.yaml
.ipynb_checkpoints/

19
configs/azure_openai.yaml Normal file
View File

@@ -0,0 +1,19 @@
app:
config:
id: azure-openai-app
llm:
provider: azure_openai
model: gpt-35-turbo
config:
deployment_name: your_llm_deployment_name
temperature: 0.5
max_tokens: 1000
top_p: 1
stream: false
embedder:
provider: azure_openai
config:
model: text-embedding-ada-002
deployment_name: you_embedding_model_deployment_name

40
docs/components/embedding-models.mdx
View File

@@ -8,6 +8,7 @@ Embedchain supports several embedding models from the following providers:
<CardGroup cols={4}>
<Card title="OpenAI" href="#openai"></Card>
<Card title="Azure OpenAI" href="#azure-openai"></Card>
<Card title="GPT4All" href="#gpt4all"></Card>
<Card title="Hugging Face" href="#hugging-face"></Card>
<Card title="Vertex AI" href="#vertex-ai"></Card>
@@ -43,6 +44,45 @@ embedder:
</CodeGroup>
## Azure OpenAI
To use Azure OpenAI embedding model, you have to set some of the azure openai related environment variables as given in the code block below:
<CodeGroup>
```python main.py
import os
from embedchain import App
os.environ["OPENAI_API_TYPE"] = "azure"
os.environ["OPENAI_API_BASE"] = "https://xxx.openai.azure.com/"
os.environ["OPENAI_API_KEY"] = "xxx"
os.environ["OPENAI_API_VERSION"] = "xxx"
app = App.from_config(yaml_path="config.yaml")
```
```yaml config.yaml
llm:
provider: azure_openai
model: gpt-35-turbo
config:
deployment_name: your_llm_deployment_name
temperature: 0.5
max_tokens: 1000
top_p: 1
stream: false
embedder:
provider: azure_openai
config:
model: text-embedding-ada-002
deployment_name: you_embedding_model_deployment_name
```
</CodeGroup>
You can find the list of models and deployment name on the [Azure OpenAI Platform](https://oai.azure.com/portal).
## GPT4ALL
GPT4All supports generating high quality embeddings of arbitrary length documents of text using a CPU optimized contrastively trained Sentence Transformer.

37
docs/components/llms.mdx
View File

@@ -65,7 +65,42 @@ llm:
## Azure OpenAI
_Coming soon_
To use Azure OpenAI model, you have to set some of the azure openai related environment variables as given in the code block below:
<CodeGroup>
```python main.py
import os
from embedchain import App
os.environ["OPENAI_API_TYPE"] = "azure"
os.environ["OPENAI_API_BASE"] = "https://xxx.openai.azure.com/"
os.environ["OPENAI_API_KEY"] = "xxx"
os.environ["OPENAI_API_VERSION"] = "xxx"
app = App.from_config(yaml_path="config.yaml")
```
```yaml config.yaml
llm:
provider: azure_openai
model: gpt-35-turbo
config:
deployment_name: your_llm_deployment_name
temperature: 0.5
max_tokens: 1000
top_p: 1
stream: false
embedder:
provider: azure_openai
config:
model: text-embedding-ada-002
deployment_name: you_embedding_model_deployment_name
```
</CodeGroup>
You can find the list of models and deployment name on the [Azure OpenAI Platform](https://oai.azure.com/portal).
## Anthropic

16
docs/components/vector-databases.mdx
View File

@@ -119,11 +119,17 @@ Install related dependencies using the following command:
pip install --upgrade 'embedchain[milvus]'
```
Set the Zilliz environment variables `ZILLIZ_CLOUD_URI` and `ZILLIZ_CLOUD_TOKEN` which you can find it on their [cloud platform](https://cloud.zilliz.com/).
<CodeGroup>
```python main.py
import os
from embedchain import App
os.environ['ZILLIZ_CLOUD_URI'] = 'https://xxx.zillizcloud.com'
os.environ['ZILLIZ_CLOUD_TOKEN'] = 'xxx'
# load zilliz configuration from yaml file
app = App.from_config(yaml_path="config.yaml")
```
@@ -147,8 +153,16 @@ _Coming soon_
## Pinecone
Install pinecone related dependencies using the following command:
```bash
pip install --upgrade 'embedchain[pinecone]'
```
In order to use Pinecone as vector database, set the environment variables `PINECONE_API_KEY` and `PINECONE_ENV` which you can find on [Pinecone dashboard](https://app.pinecone.io/).
<CodeGroup>
```python main.py
from embedchain import App
@@ -165,6 +179,8 @@ vectordb:
collection_name: my-pinecone-index
```
</CodeGroup>
## Qdrant
_Coming soon_

2
embedchain/factory.py
View File

@@ -44,10 +44,12 @@ class EmbedderFactory:
"gpt4all": "embedchain.embedder.gpt4all.GPT4AllEmbedder",
"huggingface": "embedchain.embedder.huggingface.HuggingFaceEmbedder",
"vertexai": "embedchain.embedder.vertexai.VertexAIEmbedder",
"azure_openai": "embedchain.embedder.openai.OpenAIEmbedder",
"openai": "embedchain.embedder.openai.OpenAIEmbedder",
}
provider_to_config_class = {
"openai": "embedchain.config.embedder.base.BaseEmbedderConfig",
"azure_openai": "embedchain.config.embedder.base.BaseEmbedderConfig",
}
@classmethod

182
notebooks/azure-openai.ipynb Normal file
View File

@@ -0,0 +1,182 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "63ab5e89",
"metadata": {},
"source": [
"## Cookbook for using Azure OpenAI with Embedchain"
]
},
{
"cell_type": "markdown",
"id": "e32a0265",
"metadata": {},
"source": [
"### Step-1: Install embedchain package"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b80ff15a",
"metadata": {},
"outputs": [],
"source": [
"!pip install embedchain"
]
},
{
"cell_type": "markdown",
"id": "ac982a56",
"metadata": {},
"source": [
"### Step-2: Set Azure OpenAI related environment variables\n",
"\n",
"You can find these env variables on your Azure OpenAI dashboard."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e0a36133",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"from embedchain import App\n",
"\n",
"os.environ[\"OPENAI_API_TYPE\"] = \"azure\"\n",
"os.environ[\"OPENAI_API_BASE\"] = \"https://xxx.openai.azure.com/\"\n",
"os.environ[\"OPENAI_API_KEY\"] = \"xxx\"\n",
"os.environ[\"OPENAI_API_VERSION\"] = \"xxx\""
]
},
{
"cell_type": "markdown",
"id": "7d7b554e",
"metadata": {},
"source": [
"### Step-3: Define your llm and embedding model config"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b9f52fc5",
"metadata": {},
"outputs": [],
"source": [
"config = \"\"\"\n",
"llm:\n",
" provider: azure_openai\n",
" model: gpt-35-turbo\n",
" config:\n",
" deployment_name: ec_openai_azure\n",
" temperature: 0.5\n",
" max_tokens: 1000\n",
" top_p: 1\n",
" stream: false\n",
"\n",
"embedder:\n",
" provider: azure_openai\n",
" config:\n",
" model: text-embedding-ada-002\n",
" deployment_name: ec_embeddings_ada_002\n",
"\"\"\"\n",
"\n",
"# Write the multi-line string to a YAML file\n",
"with open('azure_openai.yaml', 'w') as file:\n",
" file.write(config)"
]
},
{
"cell_type": "markdown",
"id": "98a11130",
"metadata": {},
"source": [
"### Step-4 Create embedchain app based on the config"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "1ee9bdd9",
"metadata": {},
"outputs": [],
"source": [
"app = App.from_config(yaml_path=\"azure_openai.yaml\")"
]
},
{
"cell_type": "markdown",
"id": "554dc97b",
"metadata": {},
"source": [
"### Step-5: Add data sources to your app"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "686ae765",
"metadata": {},
"outputs": [],
"source": [
"app.add(\"https://www.forbes.com/profile/elon-musk\")"
]
},
{
"cell_type": "markdown",
"id": "ccc7d421",
"metadata": {},
"source": [
"### Step-6: All set. Now start asking questions related to your data"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "27868a7d",
"metadata": {},
"outputs": [],
"source": [
"while(True):\n",
" question = input(\"Enter question: \")\n",
" if question in ['q', 'exit', 'quit']\n",
" break\n",
" answer = app.query(question)\n",
" print(answer)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e1f2ead5",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
}
},
"nbformat": 4,
"nbformat_minor": 5
}