返回提交历史
Modified
.github/workflows/copilot.yml
+12
-8
Modified
docs/providers-and-models.md
+1
-3
Modified
g4f/Provider/BlackboxAPI.py
+0
-2
Modified
g4f/Provider/DDG.py
+3
-3
Modified
g4f/Provider/hf/HuggingFaceInference.py
+18
-14
Modified
g4f/Provider/needs_auth/Cerebras.py
+4
-3
Modified
g4f/models.py
+3
-3
XFEstudio/gpt4free
Small fixes and updates around various providers (#2717)
* Update DDG.py: added Llama 3.3 Instruct and o3-mini Duck.ai now supports o3-mini, and previous Llama 3.1 70B is now replaced by Llama 3.3 70B. * Update DDG.py: change Llama 3.3 70B Instruct ID to "meta-llama/Llama-3.3-70B-Instruct-Turbo" Fixed typo in full model name * Update Cerebras.py: add "deepseek-r1-distill-llama-70b" to the models list Cerebras now provides inference for a DeepSeek-R1 distilled to Llama 3.3 70B as well. * Update models.py: reflect changes in DDG provider - Removed DDG from best providers list for Llama 3.1 70B - Added DDG to best providers list for o3-mini and Llama 3.3 70B * A small update in HuggingFaceInference get_models() method Previously, get_models() method was returning "TypeError: string indices must be integers, not 'str' on line 31" from time to time, possibly because of network error so the models list couldn't load and method was trying to parse this data. Now the code is updated in order to check for any potential errors first. * Update BlackboxAPI.py: remove unused imports format_prompt() and JSON library are not being used here, so they may be removed safely. * Update copilot.yml This job is failing due to the error in JavaScript code; this commit is trying to fix it. * Update providers-and-models.md to reflect latest changes Updated models list and removed providers that are currently not working.
68414ece
代码差异
7 个文件
+41
-36
@@ -27,14 +27,18 @@ jobs:
27
27
let matchArtifact = allArtifacts.data.artifacts.filter((artifact) => {
28
28
return artifact.name == "pr_number"
29
29
})[0];
30
let download = await github.rest.actions.downloadArtifact({
31
owner: context.repo.owner,
32
repo: context.repo.repo,
33
artifact_id: matchArtifact.id,
34
archive_format: 'zip',
35
});
36
let fs = require('fs');
37
fs.writeFileSync(`${process.env.GITHUB_WORKSPACE}/pr_number.zip`, Buffer.from(download.data));
30
if (matchArtifact) {
31
let download = await github.rest.actions.downloadArtifact({
32
owner: context.repo.owner,
33
repo: context.repo.repo,
34
artifact_id: matchArtifact.id,
35
archive_format: 'zip',
36
});
37
let fs = require('fs');
38
fs.writeFileSync(`${process.env.GITHUB_WORKSPACE}/pr_number.zip`, Buffer.from(download.data));
39
} else {
40
throw new Error('No artifact found with name "pr_number"');
41
}
38
42
- name: 'Unzip artifact'
39
43
run: unzip pr_number.zip
40
44
- name: Setup Python
@@ -37,7 +37,6 @@ This document provides an overview of various AI providers and models, including
37
37
### Providers No auth required
38
38
| Website | API Credentials | Provider | Text Models | Image Models | Vision (Image Upload) | Stream | Status |
39
39
|----------|-------------|--------------|---------------|--------|--------|------|------|
40
|[aichatfree.info](https://aichatfree.info)|No auth required|`g4f.Provider.AIChatFree`|`gemini-1.5-pro` _**(1+)**_|❌|❌|✔||
41
40
|[blackbox.ai](https://www.blackbox.ai)|No auth required|`g4f.Provider.Blackbox`|`blackboxai, gpt-4, gpt-4o, o3-mini, gemini-1.5-flash, gemini-1.5-pro, blackboxai-pro, llama-3.1-8b, llama-3.1-70b, llama-3-1-405b, llama-3.3-70b, mixtral-small-28b, deepseek-chat, dbrx-instruct, qwq-32b, hermes-2-dpo, deepseek-r1, gemini-2.0-flash` _**(+32)**_|`flux`|`blackboxai, gpt-4o, o3-mini, gemini-1.5-pro, gemini-1.5-flash, llama-3.1-8b, llama-3.1-70b, llama-3.1-405b, gemini-2.0-flash`|✔||
42
41
|[api.blackbox.ai](https://api.blackbox.ai)|No auth required|`g4f.Provider.BlackboxAPI`|`deepseek-v3, deepseek-r1, deepseek-chat, mixtral-small-28b, dbrx-instruct, qwq-32b, hermes-2-dpo`|❌|❌|✔||
43
42
|[chatglm.cn](https://chatglm.cn)|No auth required|`g4f.Provider.ChatGLM`|`glm-4`|❌|❌|✔||
@@ -45,13 +44,12 @@ This document provides an overview of various AI providers and models, including
45
44
|[chatgpt.es](https://chatgpt.es)|No auth required|`g4f.Provider.ChatGptEs`|`gpt-4, gpt-4o, gpt-4o-mini`|❌|❌|✔||
46
45
|[playground.ai.cloudflare.com](https://playground.ai.cloudflare.com)|[Automatic cookies](https://playground.ai.cloudflare.com)|`g4f.Provider.Cloudflare`|`llama-2-7b, llama-3-8b, llama-3.1-8b, llama-3.2-1b, qwen-1.5-7b`|❌|❌|✔||❌|
47
46
|[copilot.microsoft.com](https://copilot.microsoft.com)|Optional API key|`g4f.Provider.Copilot`|`gpt-4, gpt-4o`|❌|❌|✔||
48
|[duckduckgo.com/aichat](https://duckduckgo.com/aichat)|No auth required|`g4f.Provider.DDG`|`gpt-4, gpt-4o-mini, claude-3-haiku, llama-3.1-70b, mixtral-8x7b`|❌|❌|✔||
47
|[duckduckgo.com/aichat](https://duckduckgo.com/aichat)|No auth required|`g4f.Provider.DDG`|`o3-mini, gpt-4, gpt-4o-mini, claude-3-haiku, llama-3.3-70b, mixtral-8x7b`|❌|❌|✔||
49
48
|[deepinfra.com/chat](https://deepinfra.com/chat)|No auth required|`g4f.Provider.DeepInfraChat`|`llama-3.1-8b, llama-3.2-90b, llama-3.3-70b, deepseek-v3, mixtral-small-28b, deepseek-r1, phi-4, wizardlm-2-8x22b, qwen-2.5-72b, yi-34b, qwen-2-72b, dolphin-2.6, dolphin-2.9, dbrx-instruct, airoboros-70b, lzlv-70b, wizardlm-2-7b, mixtral-8x22b, minicpm-2.5`|❌|`llama-3.2-90b, minicpm-2.5`|✔||
50
49
|[chat10.free2gpt.xyz](https://chat10.free2gpt.xyz)|No auth required|`g4f.Provider.Free2GPT`|`mistral-7b`|❌|❌|✔||
51
50
|[freegptsnav.aifree.site](https://freegptsnav.aifree.site)|No auth required|`g4f.Provider.FreeGpt`|`gemini-1.5-pro`|❌|❌|✔||
52
51
|[app.giz.ai/assistant](https://app.giz.ai/assistant)|No auth required|`g4f.Provider.GizAI`|`gemini-1.5-flash`|❌|❌|✔||
53
52
|[glider.so](https://glider.so)|No auth required|`g4f.Provider.Glider`|`llama-3.1-70b, llama-3.1-8b, llama-3.2-3b, deepseek-r1`|❌|❌|✔||
54
|[gprochat.com](https://gprochat.com)|No auth required|`g4f.Provider.GPROChat`|`gemini-1.5-pro`|❌|❌|✔||
55
53
|[hailuo.ai](https://www.hailuo.ai)|No auth required|`g4f.Provider.HailuoAI`|`MiniMax` _**(1)**_|❌|❌|✔||
56
54
|[editor.imagelabs.net](https://editor.imagelabs.net)|No auth required|`g4f.Provider.ImageLabs`|`gemini-1.5-pro`|❌|❌|✔||
57
55
|[editor.imagelabs.net](editor.imagelabs.net)|No auth required|`g4f.Provider.ImageLabs`|❌|`sdxl-turbo`|❌|✔||
@@ -1,11 +1,9 @@
1
1
from __future__ import annotations
2
import json
3
2
from aiohttp import ClientSession
4
3
5
4
from ..typing import AsyncResult, Messages
6
5
from .base_provider import AsyncGeneratorProvider, ProviderModelMixin
7
6
from ..requests.raise_for_status import raise_for_status
8
from .helper import format_prompt
9
7
10
8
class BlackboxAPI(AsyncGeneratorProvider, ProviderModelMixin):
11
9
label = "Blackbox AI API"
@@ -36,12 +36,12 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
36
36
supports_message_history = True
37
37
38
38
default_model = "gpt-4o-mini"
39
models = [default_model, "claude-3-haiku-20240307", "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "mistralai/Mixtral-8x7B-Instruct-v0.1"]
39
models = [default_model, "o3-mini", "claude-3-haiku-20240307", "meta-llama/Llama-3.3-70B-Instruct-Turbo", "mistralai/Mixtral-8x7B-Instruct-v0.1"]
40
40
41
41
model_aliases = {
42
42
"gpt-4": "gpt-4o-mini",
43
43
"claude-3-haiku": "claude-3-haiku-20240307",
44
"llama-3.1-70b": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
44
"llama-3.3-70b": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
45
45
"mixtral-8x7b": "mistralai/Mixtral-8x7B-Instruct-v0.1",
46
46
}
47
47
@@ -179,4 +179,4 @@ class DDG(AsyncGeneratorProvider, ProviderModelMixin):
179
179
yield FinishReason(reason)
180
180
181
181
except asyncio.TimeoutError as e:
182
raise TimeoutError(f"Request timed out: {str(e)}")
182
raise TimeoutError(f"Request timed out: {str(e)}")
@@ -25,19 +25,23 @@ class HuggingFaceInference(AsyncGeneratorProvider, ProviderModelMixin):
25
25
26
26
@classmethod
27
27
def get_models(cls) -> list[str]:
28
if not cls.models:
29
models = fallback_models.copy()
30
url = "https://huggingface.co/api/models?inference=warm&pipeline_tag=text-generation"
31
extra_models = [model["id"] for model in requests.get(url).json()]
32
extra_models.sort()
33
models.extend([model for model in extra_models if model not in models])
34
if not cls.image_models:
35
url = "https://huggingface.co/api/models?pipeline_tag=text-to-image"
36
cls.image_models = [model["id"] for model in requests.get(url).json() if model["trendingScore"] >= 20]
37
cls.image_models.sort()
38
models.extend([model for model in cls.image_models if model not in models])
39
cls.models = models
40
return cls.models
28
if not cls.models:
29
models = fallback_models.copy()
30
url = "https://huggingface.co/api/models?inference=warm&pipeline_tag=text-generation"
31
response = requests.get(url)
32
response.raise_for_status()
33
extra_models = [model["id"] for model in response.json()]
34
extra_models.sort()
35
models.extend([model for model in extra_models if model not in models])
36
if not cls.image_models:
37
url = "https://huggingface.co/api/models?pipeline_tag=text-to-image"
38
response = requests.get(url)
39
response.raise_for_status()
40
cls.image_models = [model["id"] for model in response.json() if model.get("trendingScore", 0) >= 20]
41
cls.image_models.sort()
42
models.extend([model for model in cls.image_models if model not in models])
43
cls.models = models
44
return cls.models
41
45
42
46
@classmethod
43
47
async def create_async_generator(
@@ -215,4 +219,4 @@ def get_inputs(messages: Messages, model_data: dict, model_type: str, do_continu
215
219
inputs = format_prompt(messages, do_continue=do_continue)
216
220
else:
217
221
inputs = format_prompt(messages, do_continue=do_continue)
218
return inputs
222
return inputs
@@ -17,9 +17,10 @@ class Cerebras(OpenaiAPI):
17
17
models = [
18
18
default_model,
19
19
"llama3.1-8b",
20
"llama-3.3-70b"
20
"llama-3.3-70b",
21
"deepseek-r1-distill-llama-70b"
21
22
]
22
model_aliases = {"llama-3.1-70b": default_model, "llama-3.1-8b": "llama3.1-8b"}
23
model_aliases = {"llama-3.1-70b": default_model, "llama-3.1-8b": "llama3.1-8b", "deepseek-r1": "deepseek-r1-distill-llama-70b"}
23
24
24
25
@classmethod
25
26
async def create_async_generator(
@@ -48,4 +49,4 @@ class Cerebras(OpenaiAPI):
48
49
},
49
50
**kwargs
50
51
):
51
yield chunk
52
yield chunk
@@ -152,7 +152,7 @@ o1_mini = Model(
152
152
o3_mini = Model(
153
153
name = 'o3-mini',
154
154
base_provider = 'OpenAI',
155
best_provider = Blackbox
155
best_provider = IterListProvider([DDG, Blackbox])
156
156
)
157
157
158
158
### GigaChat ###
@@ -198,7 +198,7 @@ llama_3_1_8b = Model(
198
198
llama_3_1_70b = Model(
199
199
name = "llama-3.1-70b",
200
200
base_provider = "Meta Llama",
201
best_provider = IterListProvider([DDG, Blackbox, Glider, Jmuz, TeachAnything])
201
best_provider = IterListProvider([Blackbox, Glider, Jmuz, TeachAnything])
202
202
)
203
203
204
204
llama_3_1_405b = Model(
@@ -236,7 +236,7 @@ llama_3_2_90b = Model(
236
236
llama_3_3_70b = Model(
237
237
name = "llama-3.3-70b",
238
238
base_provider = "Meta Llama",
239
best_provider = IterListProvider([Blackbox, DeepInfraChat, PollinationsAI, Jmuz, HuggingChat, HuggingFace])
239
best_provider = IterListProvider([DDG, Blackbox, DeepInfraChat, PollinationsAI, Jmuz, HuggingChat, HuggingFace])
240
240
)
241
241
242
242
### Mistral ###