tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-18 08:25:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #3594 from rkataria1000/duplicate_code

Browse Source 
Duplicate code
This commit is contained in:
Krish Dholakia
2024-05-13 22:02:50 -07:00
committed by GitHub
parent e9d379446d d57ecf3371
commit 901254d31e
3 changed files with 7 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/caching.py
+7 -14
View File
@@ -373,11 +373,12 @@ class RedisCache(BaseCache):
print_verbose(
f"Set ASYNC Redis Cache PIPELINE: key: {cache_key}\nValue {cache_value}\nttl={ttl}"
)
json_cache_value = json.dumps(cache_value)
# Set the value with a TTL if it's provided.
if ttl is not None:
pipe.setex(cache_key, ttl, json.dumps(cache_value))
pipe.setex(cache_key, ttl, json_cache_value)
else:
pipe.set(cache_key, json.dumps(cache_value))
pipe.set(cache_key, json_cache_value)
# Execute the pipeline and return the results.
results = await pipe.execute()
@@ -810,9 +811,7 @@ class RedisSemanticCache(BaseCache):
# get the prompt
messages = kwargs["messages"]
prompt = ""
for message in messages:
prompt += message["content"]
prompt = "".join(message["content"] for message in messages)
# create an embedding for prompt
embedding_response = litellm.embedding(
@@ -847,9 +846,7 @@ class RedisSemanticCache(BaseCache):
# get the messages
messages = kwargs["messages"]
prompt = ""
for message in messages:
prompt += message["content"]
prompt = "".join(message["content"] for message in messages)
# convert to embedding
embedding_response = litellm.embedding(
@@ -909,9 +906,7 @@ class RedisSemanticCache(BaseCache):
# get the prompt
messages = kwargs["messages"]
prompt = ""
for message in messages:
prompt += message["content"]
prompt = "".join(message["content"] for message in messages)
# create an embedding for prompt
router_model_names = (
[m["model_name"] for m in llm_model_list]
@@ -964,9 +959,7 @@ class RedisSemanticCache(BaseCache):
# get the messages
messages = kwargs["messages"]
prompt = ""
for message in messages:
prompt += message["content"]
prompt = "".join(message["content"] for message in messages)
router_model_names = (
[m["model_name"] for m in llm_model_list]
litellm/router_strategy/lowest_cost.py
-3
View File
@@ -101,9 +101,6 @@ class LowestCostLoggingHandler(CustomLogger):
if precise_minute not in request_count_dict[id]:
request_count_dict[id][precise_minute] = {}
if precise_minute not in request_count_dict[id]:
request_count_dict[id][precise_minute] = {}
## TPM
request_count_dict[id][precise_minute]["tpm"] = (
request_count_dict[id][precise_minute].get("tpm", 0) + total_tokens
litellm/router_strategy/lowest_latency.py
-3
View File
@@ -115,9 +115,6 @@ class LowestLatencyLoggingHandler(CustomLogger):
if precise_minute not in request_count_dict[id]:
request_count_dict[id][precise_minute] = {}
if precise_minute not in request_count_dict[id]:
request_count_dict[id][precise_minute] = {}
## TPM
request_count_dict[id][precise_minute]["tpm"] = (
request_count_dict[id][precise_minute].get("tpm", 0) + total_tokens