dale_yxc/ragflow_python
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Feature/feat1017 (#2872)

Browse Source 
### What problem does this PR solve?

1. fix: mid map show error in knowledge graph, juse because
```@antv/g6```version changed
2. feat: concurrent threads configuration support in graph extractor
3. fix: used tokens update failed for tenant
4. feat: timeout configuration support for llm
5. fix: regex error in graph extractor
6. feat: qwen rerank(```gte-rerank```) support
7. fix: timeout deal in knowledge graph index process. Now chat by
stream output, also, it is configuratable.
8. feat: ```qwen-long``` model configuration

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: chongchuanbing <chongchuanbing@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
This commit is contained in:
chongchuanbing
2024-10-21 12:11:08 +08:00
committed by GitHub
parent 4bdf3fd48e
commit ac26d09a59
8 changed files with 95 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

58
rag/llm/chat_model.py
View File

@@ -31,7 +31,8 @@ import asyncio
class Base(ABC):
def __init__(self, key, model_name, base_url):
self.client = OpenAI(api_key=key, base_url=base_url)
timeout = int(os.environ.get('LM_TIMEOUT_SECONDS', 600))
self.client = OpenAI(api_key=key, base_url=base_url, timeout=timeout)
self.model_name = model_name
def chat(self, system, history, gen_conf):
@@ -216,28 +217,39 @@ class QWenChat(Base):
self.model_name = model_name
def chat(self, system, history, gen_conf):
from http import HTTPStatus
if system:
history.insert(0, {"role": "system", "content": system})
response = Generation.call(
self.model_name,
messages=history,
result_format='message',
**gen_conf
)
ans = ""
tk_count = 0
if response.status_code == HTTPStatus.OK:
ans += response.output.choices[0]['message']['content']
tk_count += response.usage.total_tokens
if response.output.choices[0].get("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, tk_count
stream_flag = str(os.environ.get('QWEN_CHAT_BY_STREAM', 'true')).lower() == 'true'
if not stream_flag:
from http import HTTPStatus
if system:
history.insert(0, {"role": "system", "content": system})
return "**ERROR**: " + response.message, tk_count
response = Generation.call(
self.model_name,
messages=history,
result_format='message',
**gen_conf
)
ans = ""
tk_count = 0
if response.status_code == HTTPStatus.OK:
ans += response.output.choices[0]['message']['content']
tk_count += response.usage.total_tokens
if response.output.choices[0].get("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, tk_count
def chat_streamly(self, system, history, gen_conf):
return "**ERROR**: " + response.message, tk_count
else:
g = self._chat_streamly(system, history, gen_conf, incremental_output=True)
result_list = list(g)
error_msg_list = [item for item in result_list if str(item).find("**ERROR**") >= 0]
if len(error_msg_list) > 0:
return "**ERROR**: " + "".join(error_msg_list) , 0
else:
return "".join(result_list[:-1]), result_list[-1]
def _chat_streamly(self, system, history, gen_conf, incremental_output=False):
from http import HTTPStatus
if system:
history.insert(0, {"role": "system", "content": system})
@@ -249,6 +261,7 @@ class QWenChat(Base):
messages=history,
result_format='message',
stream=True,
incremental_output=incremental_output,
**gen_conf
)
for resp in response:
@@ -267,6 +280,9 @@ class QWenChat(Base):
yield tk_count
def chat_streamly(self, system, history, gen_conf):
return self._chat_streamly(system, history, gen_conf)
class ZhipuChat(Base):
def __init__(self, key, model_name="glm-3-turbo", **kwargs):