summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorHeiner Lohaus <hlohaus@users.noreply.github.com>2024-05-20 15:59:06 +0200
committerHeiner Lohaus <hlohaus@users.noreply.github.com>2024-05-20 15:59:06 +0200
commit77a1f500a88a040aca5935510cce5e2356f652d2 (patch)
tree936bc18ad7bc053cedba9897d6032c032e5bb19f
parentMerge pull request #1984 from hlohaus/leech (diff)
downloadgpt4free-77a1f500a88a040aca5935510cce5e2356f652d2.tar
gpt4free-77a1f500a88a040aca5935510cce5e2356f652d2.tar.gz
gpt4free-77a1f500a88a040aca5935510cce5e2356f652d2.tar.bz2
gpt4free-77a1f500a88a040aca5935510cce5e2356f652d2.tar.lz
gpt4free-77a1f500a88a040aca5935510cce5e2356f652d2.tar.xz
gpt4free-77a1f500a88a040aca5935510cce5e2356f652d2.tar.zst
gpt4free-77a1f500a88a040aca5935510cce5e2356f652d2.zip
-rw-r--r--docs/async_client.md43
-rw-r--r--etc/examples/image_api.py9
-rw-r--r--g4f/gui/client/static/css/style.css3
3 files changed, 51 insertions, 4 deletions
diff --git a/docs/async_client.md b/docs/async_client.md
index 4827d11b..ad08302c 100644
--- a/docs/async_client.md
+++ b/docs/async_client.md
@@ -9,15 +9,39 @@ Designed to maintain compatibility with the existing OpenAI API, the G4F AsyncCl
The G4F AsyncClient API offers several key features:
- **Custom Providers:** The G4F Client API allows you to use custom providers. This feature enhances the flexibility of the API, enabling it to cater to a wide range of use cases.
-
- **ChatCompletion Interface:** The G4F package provides an interface for interacting with chat models through the ChatCompletion class. This class provides methods for creating both streaming and non-streaming responses.
-
- **Streaming Responses:** The ChatCompletion.create method can return a response iteratively as and when they are received if the stream parameter is set to True.
-
- **Non-Streaming Responses:** The ChatCompletion.create method can also generate non-streaming responses.
+- **Image Generation and Vision Models:** The G4F Client API also supports image generation and vision models, expanding its utility beyond text-based interactions.
+
+## Initializing the Client
+
+To utilize the G4F AsyncClient, create a new instance. Below is an example showcasing custom providers:
+
+```python
+from g4f.client import AsyncClient
+from g4f.Provider import BingCreateImages, OpenaiChat, Gemini
-- **Image Generation and Vision Models:** The G4F Client API also supports image generation and vision models, expanding its utility beyond text-based interactions.
+client = AsyncClient(
+ provider=OpenaiChat,
+ image_provider=Gemini,
+ ...
+)
+```
+
+## Configuration
+You can set an "api_key" for your provider in the client. You also have the option to define a proxy for all outgoing requests:
+
+```python
+from g4f.client import AsyncClient
+
+client = AsyncClient(
+ api_key="...",
+ proxies="http://user:pass@host",
+ ...
+)
+```
## Using AsyncClient
@@ -62,6 +86,17 @@ response = await client.images.generate(
image_url = response.data[0].url
```
+#### Base64 as the response format
+
+```python
+response = await client.images.generate(
+ prompt="a cool cat",
+ response_format="b64_json"
+)
+
+base64_text = response.data[0].b64_json
+```
+
### Example usage with asyncio.gather
Start two tasks at the same time:
diff --git a/etc/examples/image_api.py b/etc/examples/image_api.py
new file mode 100644
index 00000000..dbae22ed
--- /dev/null
+++ b/etc/examples/image_api.py
@@ -0,0 +1,9 @@
+import requests
+url = "http://localhost:1337/v1/images/generations"
+body = {
+ "prompt": "heaven for dogs",
+ "provider": "OpenaiAccount",
+ "response_format": "b64_json",
+}
+data = requests.post(url, json=body, stream=True).json()
+print(data) \ No newline at end of file
diff --git a/g4f/gui/client/static/css/style.css b/g4f/gui/client/static/css/style.css
index e8ed0a6f..f3a4708d 100644
--- a/g4f/gui/client/static/css/style.css
+++ b/g4f/gui/client/static/css/style.css
@@ -1143,4 +1143,7 @@ a:-webkit-any-link {
.message .user {
display: none;
}
+ .message.regenerate {
+ opacity: 1;
+ }
} \ No newline at end of file