phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Squashed commit of the following: (#9709)

Browse source 
commit b12a9892b7
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Wed Apr 2 08:09:56 2025 -0700

    fix(utils.py): don't modify openai_token_counter

commit 294de31803
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 21:22:40 2025 -0700

    fix: fix linting error

commit cb6e9fbe40
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 19:52:45 2025 -0700

    refactor: complete migration

commit bfc159172d
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 19:09:59 2025 -0700

    refactor: refactor more constants

commit 43ffb6a558
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:45:24 2025 -0700

    fix: test

commit 04dbe4310c
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:28:58 2025 -0700

    refactor: refactor: move more constants into constants.py

commit 3c26284aff
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:14:46 2025 -0700

    refactor: migrate hardcoded constants out of __init__.py

commit c11e0de69d
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:11:21 2025 -0700

    build: migrate all constants into constants.py

commit 7882bdc787
Author: Krrish Dholakia <krrishdholakia@gmail.com>
Date:   Mon Mar 24 18:07:37 2025 -0700

    build: initial test banning hardcoded numbers in repo
This commit is contained in:
Krish Dholakia 2025-04-02 21:24:54 -07:00 • committed by GitHub
parent 5a722ef18f
commit 8ee32291e0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
51 changed files with 509 additions and 118 deletions
Download patch file Download diff file Expand all files Collapse all files

34
litellm/caching/qdrant_semantic_cache.py
View file

@ -11,10 +11,12 @@ Has 4 methods:
import ast
import asyncio
import json
from typing import Any
from typing import Any, cast
import litellm
from litellm._logging import print_verbose
from litellm.constants import QDRANT_SCALAR_QUANTILE, QDRANT_VECTOR_SIZE
from litellm.types.utils import EmbeddingResponse
from .base_cache import BaseCache
@ -118,7 +120,11 @@ class QdrantSemanticCache(BaseCache):
}
elif quantization_config == "scalar":
quantization_params = {
"scalar": {"type": "int8", "quantile": 0.99, "always_ram": False}
"scalar": {
"type": "int8",
"quantile": QDRANT_SCALAR_QUANTILE,
"always_ram": False,
}
}
elif quantization_config == "product":
quantization_params = {
@ -132,7 +138,7 @@ class QdrantSemanticCache(BaseCache):
new_collection_status = self.sync_client.put(
url=f"{self.qdrant_api_base}/collections/{self.collection_name}",
json={
"vectors": {"size": 1536, "distance": "Cosine"},
"vectors": {"size": QDRANT_VECTOR_SIZE, "distance": "Cosine"},
"quantization_config": quantization_params,
},
headers=self.headers,
@ -171,10 +177,13 @@ class QdrantSemanticCache(BaseCache):
prompt += message["content"]
# create an embedding for prompt
embedding_response = litellm.embedding(
model=self.embedding_model,
input=prompt,
cache={"no-store": True, "no-cache": True},
embedding_response = cast(
EmbeddingResponse,
litellm.embedding(
model=self.embedding_model,
input=prompt,
cache={"no-store": True, "no-cache": True},
),
)
# get the embedding
@ -212,10 +221,13 @@ class QdrantSemanticCache(BaseCache):
prompt += message["content"]
# convert to embedding
embedding_response = litellm.embedding(
model=self.embedding_model,
input=prompt,
cache={"no-store": True, "no-cache": True},
embedding_response = cast(
EmbeddingResponse,
litellm.embedding(
model=self.embedding_model,
input=prompt,
cache={"no-store": True, "no-cache": True},
),
)
# get the embedding