Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add support for SILICONFLOW #1926

Merged
merged 2 commits into from
Aug 13, 2024
Merged

add support for SILICONFLOW #1926

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2586311
add support for SILICONFLOW
aopstudio Aug 13, 2024
f46da44
update
aopstudio Aug 13, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
286 changes: 285 additions & 1 deletion conf/llm_factories.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2767,6 +2767,290 @@
"model_type": "chat"
}
]
}
},
{
"name": "SILICONFLOW",
"logo": "",
"tags": "LLM,TEXT EMBEDDING,TEXT RE-RANK",
"status": "1",
"llm": [
{
"llm_name": "Qwen/Qwen2-7B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Qwen/Qwen2-1.5B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Qwen/Qwen1.5-7B-Chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "THUDM/glm-4-9b-chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "THUDM/chatglm3-6b",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "01-ai/Yi-1.5-9B-Chat-16K",
"tags": "LLM,CHAT,16k",
"max_tokens": 16384,
"model_type": "chat"
},
{
"llm_name": "01-ai/Yi-1.5-6B-Chat",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "google/gemma-2-9b-it",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "internlm/internlm2_5-7b-chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "meta-llama/Meta-Llama-3-8B-Instruct",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "mistralai/Mistral-7B-Instruct-v0.2",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Pro/Qwen/Qwen2-7B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Pro/Qwen/Qwen2-1.5B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Pro/Qwen/Qwen1.5-7B-Chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Pro/THUDM/glm-4-9b-chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Pro/THUDM/chatglm3-6b",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Pro/01-ai/Yi-1.5-9B-Chat-16K",
"tags": "LLM,CHAT,16k",
"max_tokens": 16384,
"model_type": "chat"
},
{
"llm_name": "Pro/01-ai/Yi-1.5-6B-Chat",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "Pro/internlm/internlm2_5-7b-chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Pro/google/gemma-2-9b-it",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "Pro/meta-llama/Meta-Llama-3.1-8B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Pro/meta-llama/Meta-Llama-3-8B-Instruct",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "Pro/mistralai/Mistral-7B-Instruct-v0.2",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Qwen/Qwen2-72B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Qwen/Qwen2-Math-72B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Qwen/Qwen2-57B-A14B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Qwen/Qwen1.5-110B-Chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Qwen/Qwen1.5-32B-Chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "Qwen/Qwen1.5-14B-Chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "01-ai/Yi-1.5-34B-Chat-16K",
"tags": "LLM,CHAT,16k",
"max_tokens": 16384,
"model_type": "chat"
},
{
"llm_name": "deepseek-ai/DeepSeek-Coder-V2-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "deepseek-ai/DeepSeek-V2-Chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "deepseek-ai/deepseek-llm-67b-chat",
"tags": "LLM,CHAT,4k",
"max_tokens": 4096,
"model_type": "chat"
},
{
"llm_name": "internlm/internlm2_5-20b-chat",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "meta-llama/Meta-Llama-3.1-405B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "meta-llama/Meta-Llama-3-70B-Instruct",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"tags": "LLM,CHAT,32k",
"max_tokens": 32768,
"model_type": "chat"
},
{
"llm_name": "google/gemma-2-27b-it",
"tags": "LLM,CHAT,8k",
"max_tokens": 8192,
"model_type": "chat"
},
{
"llm_name": "BAAI/bge-m3 ",
"tags": "TEXT EMBEDDING,8K",
"max_tokens": 8192,
"model_type": "embedding"
},
{
"llm_name": "BAAI/bge-large-en-v1.5 ",
"tags": "TEXT EMBEDDING,512",
"max_tokens": 512,
"model_type": "embedding"
},
{
"llm_name": "BAAI/bge-large-zh-v1.5 ",
"tags": "TEXT EMBEDDING,512",
"max_tokens": 512,
"model_type": "embedding"
},
{
"llm_name": "netease-youdao/bce-embedding-base_vl",
"tags": "TEXT EMBEDDING,512",
"max_tokens": 512,
"model_type": "embedding"
},
{
"llm_name": "BAAI/bge-reranker-v2-m3",
"tags": "RE-RANK, 512",
"max_tokens": 1024,
"model_type": "rerank"
},
{
"llm_name": "netease-youdao/bce-reranker-base-v1",
"tags": "RE-RANK, 512",
"max_tokens": 1024,
"model_type": "rerank"
}
]
}
]
}
9 changes: 6 additions & 3 deletions rag/llm/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,8 @@
"cohere": CoHereEmbed,
"TogetherAI": TogetherAIEmbed,
"PerfXCloud": PerfXCloudEmbed,
"Upstage": UpstageEmbed
"Upstage": UpstageEmbed,
"SILICONFLOW": SILICONFLOWEmbed
}


Expand Down Expand Up @@ -92,7 +93,8 @@
"TogetherAI": TogetherAIChat,
"PerfXCloud": PerfXCloudChat,
"Upstage":UpstageChat,
"novita.ai": NovitaAIChat
"novita.ai": NovitaAIChat,
"SILICONFLOW": SILICONFLOWChat
}


Expand All @@ -105,7 +107,8 @@
"LM-Studio": LmStudioRerank,
"OpenAI-API-Compatible": OpenAI_APIRerank,
"cohere": CoHereRerank,
"TogetherAI": TogetherAIRerank
"TogetherAI": TogetherAIRerank,
"SILICONFLOW": SILICONFLOWRerank
}


Expand Down
8 changes: 7 additions & 1 deletion rag/llm/chat_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1016,4 +1016,10 @@ def __init__(self, key, model_name, base_url="https://api.novita.ai/v3/openai"):
if not base_url:
base_url = "https://api.novita.ai/v3/openai"
super().__init__(key, model_name, base_url)



class SILICONFLOWChat(Base):
def __init__(self, key, model_name, base_url="https://api.siliconflow.cn/v1"):
if not base_url:
base_url = "https://api.siliconflow.cn/v1"
super().__init__(key, model_name, base_url)
7 changes: 7 additions & 0 deletions rag/llm/embedding_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -574,3 +574,10 @@ def __init__(self, key, model_name, base_url="https://api.upstage.ai/v1/solar"):
if not base_url:
base_url = "https://api.upstage.ai/v1/solar"
super().__init__(key, model_name, base_url)


class SILICONFLOWEmbed(OpenAIEmbed):
def __init__(self, key, model_name, base_url="https://api.siliconflow.cn/v1"):
if not base_url:
base_url = "https://api.siliconflow.cn/v1"
super().__init__(key, model_name, base_url)
37 changes: 36 additions & 1 deletion rag/llm/rerank_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -252,4 +252,39 @@ def __init__(self, key, model_name, base_url):
pass

def similarity(self, query: str, texts: list):
raise NotImplementedError("The api has not been implement")
raise NotImplementedError("The api has not been implement")


class SILICONFLOWRerank(Base):
def __init__(
self, key, model_name, base_url="https://api.siliconflow.cn/v1/rerank"
):
if not base_url:
base_url = "https://api.siliconflow.cn/v1/rerank"
self.model_name = model_name
self.base_url = base_url
self.headers = {
"accept": "application/json",
"content-type": "application/json",
"authorization": f"Bearer {key}",
}

def similarity(self, query: str, texts: list):
payload = {
"model": self.model_name,
"query": query,
"documents": texts,
"top_n": len(texts),
"return_documents": False,
"max_chunks_per_doc": 1024,
"overlap_tokens": 80,
}
response = requests.post(
self.base_url, json=payload, headers=self.headers
).json()
rank = np.array([d["relevance_score"] for d in response["results"]])
indexs = [d["index"] for d in response["results"]]
return (
rank[indexs],
response["meta"]["tokens"]["input_tokens"] + response["meta"]["tokens"]["output_tokens"],
)
6 changes: 6 additions & 0 deletions web/src/assets/svg/llm/siliconflow.svg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading