pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2026-02-02 00:25:06 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refa: ollama keep alive issue. (#8216)

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

#8122

### Type of change

- [x] Refactoring
This commit is contained in:
Kevin Hu
2025-06-12 15:09:40 +08:00
committed by GitHub
parent e7c85e569b
commit d5236b71f4
2 changed files with 6 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
rag/llm/chat_model.py
View File

@ -871,7 +871,7 @@ class OllamaChat(Base):
ctx_size = self._calculate_dynamic_ctx(history)
gen_conf["num_ctx"] = ctx_size
response = self.client.chat(model=self.model_name, messages=history, options=gen_conf)
response = self.client.chat(model=self.model_name, messages=history, options=gen_conf, keep_alive=-1)
ans = response["message"]["content"].strip()
token_count = response.get("eval_count", 0) + response.get("prompt_eval_count", 0)
return ans, token_count
@ -898,7 +898,7 @@ class OllamaChat(Base):
ans = ""
try:
response = self.client.chat(model=self.model_name, messages=history, stream=True, options=options)
response = self.client.chat(model=self.model_name, messages=history, stream=True, options=options, keep_alive=-1)
for resp in response:
if resp["done"]:
token_count = resp.get("prompt_eval_count", 0) + resp.get("eval_count", 0)