mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 19:24:27 +00:00
fix(ollama.py): fix async completion calls for ollama
This commit is contained in:
parent
aa649a8599
commit
2231601d5a
7 changed files with 35 additions and 17 deletions
|
@ -64,7 +64,7 @@ class ProxyLogging:
|
|||
1. /chat/completions
|
||||
2. /embeddings
|
||||
"""
|
||||
try:
|
||||
try:
|
||||
self.call_details["data"] = data
|
||||
self.call_details["call_type"] = call_type
|
||||
## check if max parallel requests set
|
||||
|
@ -75,6 +75,7 @@ class ProxyLogging:
|
|||
api_key=user_api_key_dict.api_key,
|
||||
user_api_key_cache=self.call_details["user_api_key_cache"])
|
||||
|
||||
print_verbose(f'final data being sent to {call_type} call: {data}')
|
||||
return data
|
||||
except Exception as e:
|
||||
raise e
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue