mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-08-14 02:05:56 +08:00
fix MiniMax api error (#1567)
### What problem does this PR solve? #1353 ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) --------- Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
This commit is contained in:
parent
fe5dd5b70a
commit
9ae57eb370
@ -558,7 +558,7 @@ class TenantLLM(DataBaseModel):
|
|||||||
null=True,
|
null=True,
|
||||||
help_text="LLM name",
|
help_text="LLM name",
|
||||||
default="")
|
default="")
|
||||||
api_key = CharField(max_length=255, null=True, help_text="API KEY")
|
api_key = CharField(max_length=1024, null=True, help_text="API KEY")
|
||||||
api_base = CharField(max_length=255, null=True, help_text="API Base")
|
api_base = CharField(max_length=255, null=True, help_text="API Base")
|
||||||
used_tokens = IntegerField(default=0)
|
used_tokens = IntegerField(default=0)
|
||||||
|
|
||||||
@ -885,3 +885,9 @@ def migrate_db():
|
|||||||
)
|
)
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
pass
|
pass
|
||||||
|
try:
|
||||||
|
migrate(
|
||||||
|
migrator.alter_column_type('tenant_llm', 'api_key', CharField(max_length=1024, null=True, help_text="API KEY"))
|
||||||
|
)
|
||||||
|
except Exception as e:
|
||||||
|
pass
|
@ -433,37 +433,37 @@
|
|||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"name": "Minimax",
|
"name": "MiniMax",
|
||||||
"logo": "",
|
"logo": "",
|
||||||
"tags": "LLM,TEXT EMBEDDING",
|
"tags": "LLM,TEXT EMBEDDING",
|
||||||
"status": "1",
|
"status": "1",
|
||||||
"llm": [
|
"llm": [
|
||||||
{
|
{
|
||||||
"llm_name": "abab6.5",
|
"llm_name": "abab6.5-chat",
|
||||||
"tags": "LLM,CHAT,8k",
|
"tags": "LLM,CHAT,8k",
|
||||||
"max_tokens": 8192,
|
"max_tokens": 8192,
|
||||||
"model_type": "chat"
|
"model_type": "chat"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"llm_name": "abab6.5s",
|
"llm_name": "abab6.5s-chat",
|
||||||
"tags": "LLM,CHAT,245k",
|
"tags": "LLM,CHAT,245k",
|
||||||
"max_tokens": 245760,
|
"max_tokens": 245760,
|
||||||
"model_type": "chat"
|
"model_type": "chat"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"llm_name": "abab6.5t",
|
"llm_name": "abab6.5t-chat",
|
||||||
"tags": "LLM,CHAT,8k",
|
"tags": "LLM,CHAT,8k",
|
||||||
"max_tokens": 8192,
|
"max_tokens": 8192,
|
||||||
"model_type": "chat"
|
"model_type": "chat"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"llm_name": "abab6.5g",
|
"llm_name": "abab6.5g-chat",
|
||||||
"tags": "LLM,CHAT,8k",
|
"tags": "LLM,CHAT,8k",
|
||||||
"max_tokens": 8192,
|
"max_tokens": 8192,
|
||||||
"model_type": "chat"
|
"model_type": "chat"
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
"llm_name": "abab5.5s",
|
"llm_name": "abab5.5s-chat",
|
||||||
"tags": "LLM,CHAT,8k",
|
"tags": "LLM,CHAT,8k",
|
||||||
"max_tokens": 8192,
|
"max_tokens": 8192,
|
||||||
"model_type": "chat"
|
"model_type": "chat"
|
||||||
|
@ -24,7 +24,8 @@ from volcengine.maas.v2 import MaasService
|
|||||||
from rag.nlp import is_english
|
from rag.nlp import is_english
|
||||||
from rag.utils import num_tokens_from_string
|
from rag.utils import num_tokens_from_string
|
||||||
from groq import Groq
|
from groq import Groq
|
||||||
|
import json
|
||||||
|
import requests
|
||||||
|
|
||||||
class Base(ABC):
|
class Base(ABC):
|
||||||
def __init__(self, key, model_name, base_url):
|
def __init__(self, key, model_name, base_url):
|
||||||
@ -475,11 +476,83 @@ class VolcEngineChat(Base):
|
|||||||
|
|
||||||
|
|
||||||
class MiniMaxChat(Base):
|
class MiniMaxChat(Base):
|
||||||
def __init__(self, key, model_name="abab6.5s-chat",
|
def __init__(
|
||||||
base_url="https://api.minimax.chat/v1/text/chatcompletion_v2"):
|
self,
|
||||||
|
key,
|
||||||
|
model_name,
|
||||||
|
base_url="https://api.minimax.chat/v1/text/chatcompletion_v2",
|
||||||
|
):
|
||||||
if not base_url:
|
if not base_url:
|
||||||
base_url="https://api.minimax.chat/v1/text/chatcompletion_v2"
|
base_url = "https://api.minimax.chat/v1/text/chatcompletion_v2"
|
||||||
super().__init__(key, model_name, base_url)
|
self.base_url = base_url
|
||||||
|
self.model_name = model_name
|
||||||
|
self.api_key = key
|
||||||
|
|
||||||
|
def chat(self, system, history, gen_conf):
|
||||||
|
if system:
|
||||||
|
history.insert(0, {"role": "system", "content": system})
|
||||||
|
for k in list(gen_conf.keys()):
|
||||||
|
if k not in ["temperature", "top_p", "max_tokens"]:
|
||||||
|
del gen_conf[k]
|
||||||
|
headers = {
|
||||||
|
"Authorization": f"Bearer {self.api_key}",
|
||||||
|
"Content-Type": "application/json",
|
||||||
|
}
|
||||||
|
payload = json.dumps(
|
||||||
|
{"model": self.model_name, "messages": history, **gen_conf}
|
||||||
|
)
|
||||||
|
try:
|
||||||
|
response = requests.request(
|
||||||
|
"POST", url=self.base_url, headers=headers, data=payload
|
||||||
|
)
|
||||||
|
print(response, flush=True)
|
||||||
|
response = response.json()
|
||||||
|
ans = response["choices"][0]["message"]["content"].strip()
|
||||||
|
if response["choices"][0]["finish_reason"] == "length":
|
||||||
|
ans += "...\nFor the content length reason, it stopped, continue?" if is_english(
|
||||||
|
[ans]) else "······\n由于长度的原因,回答被截断了,要继续吗?"
|
||||||
|
return ans, response["usage"]["total_tokens"]
|
||||||
|
except Exception as e:
|
||||||
|
return "**ERROR**: " + str(e), 0
|
||||||
|
|
||||||
|
def chat_streamly(self, system, history, gen_conf):
|
||||||
|
if system:
|
||||||
|
history.insert(0, {"role": "system", "content": system})
|
||||||
|
ans = ""
|
||||||
|
total_tokens = 0
|
||||||
|
try:
|
||||||
|
headers = {
|
||||||
|
"Authorization": f"Bearer {self.api_key}",
|
||||||
|
"Content-Type": "application/json",
|
||||||
|
}
|
||||||
|
payload = json.dumps(
|
||||||
|
{
|
||||||
|
"model": self.model_name,
|
||||||
|
"messages": history,
|
||||||
|
"stream": True,
|
||||||
|
**gen_conf,
|
||||||
|
}
|
||||||
|
)
|
||||||
|
response = requests.request(
|
||||||
|
"POST",
|
||||||
|
url=self.base_url,
|
||||||
|
headers=headers,
|
||||||
|
data=payload,
|
||||||
|
)
|
||||||
|
for resp in response.text.split("\n\n")[:-1]:
|
||||||
|
resp = json.loads(resp[6:])
|
||||||
|
if "delta" in resp["choices"][0]:
|
||||||
|
text = resp["choices"][0]["delta"]["content"]
|
||||||
|
else:
|
||||||
|
continue
|
||||||
|
ans += text
|
||||||
|
total_tokens += num_tokens_from_string(text)
|
||||||
|
yield ans
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
yield ans + "\n**ERROR**: " + str(e)
|
||||||
|
|
||||||
|
yield total_tokens
|
||||||
|
|
||||||
|
|
||||||
class MistralChat(Base):
|
class MistralChat(Base):
|
||||||
@ -748,4 +821,3 @@ class OpenRouterChat(Base):
|
|||||||
self.base_url = "https://openrouter.ai/api/v1"
|
self.base_url = "https://openrouter.ai/api/v1"
|
||||||
self.client = OpenAI(base_url=self.base_url, api_key=key)
|
self.client = OpenAI(base_url=self.base_url, api_key=key)
|
||||||
self.model_name = model_name
|
self.model_name = model_name
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user