krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-30 16:38:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

docs: OpenAI update (#693)

Browse Source 
* docs: OpenAI update

* Update qdrant-landing/content/documentation/embeddings/openai.md

Co-authored-by: Nirant <NirantK@users.noreply.github.com>

---------

Co-authored-by: Nirant <NirantK@users.noreply.github.com>
This commit is contained in:
Anush
2024-03-07 20:41:34 +05:30
committed by GitHub
co-authored by Nirant
parent 03a5f5a5b4
commit 7d0ca375b5
1 changed files with 78 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/embeddings/openai.md
+78 -21
View File
@@ -1,46 +1,103 @@
---
title: OpenAI
title: OpenAI
weight: 800
aliases: [ ../integrations/openai/ ]
---
# OpenAI
Qdrant can also easily work with [OpenAI embeddings](https://platform.openai.com/docs/guides/embeddings/embeddings).
Qdrant supports working with [OpenAI embeddings](https://platform.openai.com/docs/guides/embeddings/embeddings).
There is an official OpenAI Python package that simplifies obtaining them, and it might be installed with pip:
There is an official OpenAI Python package that simplifies obtaining them, and it can be installed with pip:
```bash
pip install openai
```
Once installed, the package exposes the method allowing to retrieve the embedding for given text. OpenAI requires an API key that has to be provided either as an environmental variable `OPENAI_API_KEY` or set in the source code directly, as presented below:
### Setting up the OpenAI and Qdrant clients
```python
import openai
import qdrant_client
from qdrant_client.http.models import Batch
# Choose one of the available models:
# https://platform.openai.com/docs/models/embeddings
embedding_model = "text-embedding-ada-002"
openai_client = openai.Client(
api_key="<< your_api_key >>"
)
response = openai_client.embeddings.create(
input="The best vector database",
model=embedding_model,
api_key="<YOUR_API_KEY>"
)
qdrant_client = qdrant_client.QdrantClient()
qdrant_client.upsert(
collection_name="MyCollection",
points=Batch(
ids=[1],
vectors=[response.data[0].embedding],
qdrant_client = qdrant_client.QdrantClient(":memory:")
texts = [
"Qdrant is the best vector search engine!",
"Loved by Enterprises and everyone building for low latency, high performance, and scale.",
]
```
The following example shows how to embed a document with the `text-embedding-3-small` model that generates sentence embeddings of size 1536. You can find the list of all supported models [here](https://platform.openai.com/docs/models/embeddings).
### Embedding a document
```python
embedding_model = "text-embedding-3-small"
result = openai_client.embeddings.create(input= texts, model=embedding_model)
```
### Converting the model outputs to Qdrant points
```python
from qdrant_client.http.models import PointStruct
points = [
PointStruct(
id=idx,
vector=data.embedding,
payload={"text": text},
)
for idx, (data, text) in enumerate(zip(result.data, texts))
]
```
### Creating a collection to insert the documents
```python
from qdrant_client.http.models import VectorParams, Distance
collection_name = "example_collection"
qdrant_client.create_collection(
collection_name,
vectors_config=VectorParams(
size=1536,
distance=Distance.COSINE,
),
)
qdrant_client.upsert(collection_name, points)
```
## Searching for documents with Qdrant
Once the documents are indexed, you can search for the most relevant documents using the same model.
```python
qdrant_client.search(
collection_name=collection_name,
query_vector=openai_client.embeddings.create(
input=["What is the best to use for vector search scaling?"],
model=embedding_model,
)
.data[0]
.embedding,
)
```
## Using OpenAI Embedding Models with Qdrant's Binary Quantization
You can use OpenAI embedding Models with [Binary Quantization](/articles/binary-quantization/) - a technique that allows you to reduce the size of the embeddings by 32 times without losing the quality of the search results too much.
|Method|Dimensionality|Test Dataset|Recall|Oversampling|
|-|-|-|-|-|
|OpenAI text-embedding-3-large|3072|[DBpedia 1M](https://huggingface.co/datasets/Qdrant/dbpedia-entities-openai3-text-embedding-3-large-3072-1M) | 0.9966|3x|
|OpenAI text-embedding-3-small|1536|[DBpedia 100K](https://huggingface.co/datasets/Qdrant/dbpedia-entities-openai3-text-embedding-3-small-1536-100K)| 0.9847|3x|
|OpenAI text-embedding-3-large|1536|[DBpedia 1M](https://huggingface.co/datasets/Qdrant/dbpedia-entities-openai3-text-embedding-3-large-1536-1M)| 0.9826|3x|
|OpenAI text-embedding-ada-002|1536|[DbPedia 1M](https://huggingface.co/datasets/KShivendu/dbpedia-entities-openai-1M) |0.98|4x|