estel/dify
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer (#17957)

Browse Source
This commit is contained in:
Bowen Liang
2025-04-30 16:07:20 +08:00
committed by GitHub
parent bcc95e520b
commit 12c96b93d9
5 changed files with 18 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
api/core/model_runtime/model_providers/__base/ai_model.py
View File

@@ -24,7 +24,6 @@ from core.model_runtime.errors.invoke import (
InvokeRateLimitError,
InvokeServerUnavailableError,
)
from core.model_runtime.model_providers.__base.tokenizers.gpt2_tokenzier import GPT2Tokenizer
from core.plugin.entities.plugin_daemon import PluginDaemonInnerError, PluginModelProviderEntity
from core.plugin.impl.model import PluginModelClient
@@ -253,15 +252,3 @@ class AIModel(BaseModel):
raise Exception(f"Invalid model parameter rule name {name}")
return default_parameter_rule
def _get_num_tokens_by_gpt2(self, text: str) -> int:
"""
Get number of tokens for given prompt messages by gpt2
Some provider models do not provide an interface for obtaining the number of tokens.
Here, the gpt2 tokenizer is used to calculate the number of tokens.
This method can be executed offline, and the gpt2 tokenizer has been cached in the project.
:param text: plain text of prompt. You need to convert the original message to plain text
:return: number of tokens
"""
return GPT2Tokenizer.get_num_tokens(text)

2
api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenzier.py
View File

@@ -30,6 +30,8 @@ class GPT2Tokenizer:
@staticmethod
def get_encoder() -> Any:
global _tokenizer, _lock
if _tokenizer is not None:
return _tokenizer
with _lock:
if _tokenizer is None:
# Try to use tiktoken to get the tokenizer because it is faster

44
api/core/rag/splitter/text_splitter.py
View File

@@ -159,50 +159,6 @@ class TextSplitter(BaseDocumentTransformer, ABC):
)
return cls(length_function=lambda x: [_huggingface_tokenizer_length(text) for text in x], **kwargs)
@classmethod
def from_tiktoken_encoder(
cls: type[TS],
encoding_name: str = "gpt2",
model_name: Optional[str] = None,
allowed_special: Union[Literal["all"], Set[str]] = set(),
disallowed_special: Union[Literal["all"], Collection[str]] = "all",
**kwargs: Any,
) -> TS:
"""Text splitter that uses tiktoken encoder to count length."""
try:
import tiktoken
except ImportError:
raise ImportError(
"Could not import tiktoken python package. "
"This is needed in order to calculate max_tokens_for_prompt. "
"Please install it with `pip install tiktoken`."
)
if model_name is not None:
enc = tiktoken.encoding_for_model(model_name)
else:
enc = tiktoken.get_encoding(encoding_name)
def _tiktoken_encoder(text: str) -> int:
return len(
enc.encode(
text,
allowed_special=allowed_special,
disallowed_special=disallowed_special,
)
)
if issubclass(cls, TokenTextSplitter):
extra_kwargs = {
"encoding_name": encoding_name,
"model_name": model_name,
"allowed_special": allowed_special,
"disallowed_special": disallowed_special,
}
kwargs = {**kwargs, **extra_kwargs}
return cls(length_function=lambda x: [_tiktoken_encoder(text) for text in x], **kwargs)
def transform_documents(self, documents: Sequence[Document], **kwargs: Any) -> Sequence[Document]:
"""Transform sequence of documents by splitting them."""
return self.split_documents(list(documents))

2
api/pyproject.toml
View File

@@ -77,7 +77,7 @@ dependencies = [
"sentry-sdk[flask]~=1.44.1",
"sqlalchemy~=2.0.29",
"starlette==0.41.0",
"tiktoken~=0.8.0",
"tiktoken~=0.9.0",
"tokenizers~=0.15.0",
"transformers~=4.35.0",
"unstructured[docx,epub,md,ppt,pptx]~=0.16.1",

30
api/uv.lock generated
View File

@@ -1398,7 +1398,7 @@ requires-dist = [
{ name = "sentry-sdk", extras = ["flask"], specifier = "~=1.44.1" },
{ name = "sqlalchemy", specifier = "~=2.0.29" },
{ name = "starlette", specifier = "==0.41.0" },
{ name = "tiktoken", specifier = "~=0.8.0" },
{ name = "tiktoken", specifier = "~=0.9.0" },
{ name = "tokenizers", specifier = "~=0.15.0" },
{ name = "transformers", specifier = "~=4.35.0" },
{ name = "unstructured", extras = ["docx", "epub", "md", "ppt", "pptx"], specifier = "~=0.16.1" },
@@ -5335,26 +5335,26 @@ wheels = [
[[package]]
name = "tiktoken"
version = "0.8.0"
version = "0.9.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "regex" },
{ name = "requests" },
]
sdist = { url = "https://files.pythonhosted.org/packages/37/02/576ff3a6639e755c4f70997b2d315f56d6d71e0d046f4fb64cb81a3fb099/tiktoken-0.8.0.tar.gz", hash = "sha256:9ccbb2740f24542534369c5635cfd9b2b3c2490754a78ac8831d99f89f94eeb2", size = 35107 }
sdist = { url = "https://files.pythonhosted.org/packages/ea/cf/756fedf6981e82897f2d570dd25fa597eb3f4459068ae0572d7e888cfd6f/tiktoken-0.9.0.tar.gz", hash = "sha256:d02a5ca6a938e0490e1ff957bc48c8b078c88cb83977be1625b1fd8aac792c5d", size = 35991 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/f6/1e/ca48e7bfeeccaf76f3a501bd84db1fa28b3c22c9d1a1f41af9fb7579c5f6/tiktoken-0.8.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d622d8011e6d6f239297efa42a2657043aaed06c4f68833550cac9e9bc723ef1", size = 1039700 },
{ url = "https://files.pythonhosted.org/packages/8c/f8/f0101d98d661b34534769c3818f5af631e59c36ac6d07268fbfc89e539ce/tiktoken-0.8.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2efaf6199717b4485031b4d6edb94075e4d79177a172f38dd934d911b588d54a", size = 982413 },
{ url = "https://files.pythonhosted.org/packages/ac/3c/2b95391d9bd520a73830469f80a96e3790e6c0a5ac2444f80f20b4b31051/tiktoken-0.8.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5637e425ce1fc49cf716d88df3092048359a4b3bbb7da762840426e937ada06d", size = 1144242 },
{ url = "https://files.pythonhosted.org/packages/01/c4/c4a4360de845217b6aa9709c15773484b50479f36bb50419c443204e5de9/tiktoken-0.8.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9fb0e352d1dbe15aba082883058b3cce9e48d33101bdaac1eccf66424feb5b47", size = 1176588 },
{ url = "https://files.pythonhosted.org/packages/f8/a3/ef984e976822cd6c2227c854f74d2e60cf4cd6fbfca46251199914746f78/tiktoken-0.8.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:56edfefe896c8f10aba372ab5706b9e3558e78db39dd497c940b47bf228bc419", size = 1237261 },
{ url = "https://files.pythonhosted.org/packages/1e/86/eea2309dc258fb86c7d9b10db536434fc16420feaa3b6113df18b23db7c2/tiktoken-0.8.0-cp311-cp311-win_amd64.whl", hash = "sha256:326624128590def898775b722ccc327e90b073714227175ea8febbc920ac0a99", size = 884537 },
{ url = "https://files.pythonhosted.org/packages/c1/22/34b2e136a6f4af186b6640cbfd6f93400783c9ef6cd550d9eab80628d9de/tiktoken-0.8.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:881839cfeae051b3628d9823b2e56b5cc93a9e2efb435f4cf15f17dc45f21586", size = 1039357 },
{ url = "https://files.pythonhosted.org/packages/04/d2/c793cf49c20f5855fd6ce05d080c0537d7418f22c58e71f392d5e8c8dbf7/tiktoken-0.8.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:fe9399bdc3f29d428f16a2f86c3c8ec20be3eac5f53693ce4980371c3245729b", size = 982616 },
{ url = "https://files.pythonhosted.org/packages/b3/a1/79846e5ef911cd5d75c844de3fa496a10c91b4b5f550aad695c5df153d72/tiktoken-0.8.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9a58deb7075d5b69237a3ff4bb51a726670419db6ea62bdcd8bd80c78497d7ab", size = 1144011 },
{ url = "https://files.pythonhosted.org/packages/26/32/e0e3a859136e95c85a572e4806dc58bf1ddf651108ae8b97d5f3ebe1a244/tiktoken-0.8.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2908c0d043a7d03ebd80347266b0e58440bdef5564f84f4d29fb235b5df3b04", size = 1175432 },
{ url = "https://files.pythonhosted.org/packages/c7/89/926b66e9025b97e9fbabeaa59048a736fe3c3e4530a204109571104f921c/tiktoken-0.8.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:294440d21a2a51e12d4238e68a5972095534fe9878be57d905c476017bff99fc", size = 1236576 },
{ url = "https://files.pythonhosted.org/packages/45/e2/39d4aa02a52bba73b2cd21ba4533c84425ff8786cc63c511d68c8897376e/tiktoken-0.8.0-cp312-cp312-win_amd64.whl", hash = "sha256:d8f3192733ac4d77977432947d563d7e1b310b96497acd3c196c9bddb36ed9db", size = 883824 },
{ url = "https://files.pythonhosted.org/packages/4d/ae/4613a59a2a48e761c5161237fc850eb470b4bb93696db89da51b79a871f1/tiktoken-0.9.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:f32cc56168eac4851109e9b5d327637f15fd662aa30dd79f964b7c39fbadd26e", size = 1065987 },
{ url = "https://files.pythonhosted.org/packages/3f/86/55d9d1f5b5a7e1164d0f1538a85529b5fcba2b105f92db3622e5d7de6522/tiktoken-0.9.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:45556bc41241e5294063508caf901bf92ba52d8ef9222023f83d2483a3055348", size = 1009155 },
{ url = "https://files.pythonhosted.org/packages/03/58/01fb6240df083b7c1916d1dcb024e2b761213c95d576e9f780dfb5625a76/tiktoken-0.9.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:03935988a91d6d3216e2ec7c645afbb3d870b37bcb67ada1943ec48678e7ee33", size = 1142898 },
{ url = "https://files.pythonhosted.org/packages/b1/73/41591c525680cd460a6becf56c9b17468d3711b1df242c53d2c7b2183d16/tiktoken-0.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8b3d80aad8d2c6b9238fc1a5524542087c52b860b10cbf952429ffb714bc1136", size = 1197535 },
{ url = "https://files.pythonhosted.org/packages/7d/7c/1069f25521c8f01a1a182f362e5c8e0337907fae91b368b7da9c3e39b810/tiktoken-0.9.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b2a21133be05dc116b1d0372af051cd2c6aa1d2188250c9b553f9fa49301b336", size = 1259548 },
{ url = "https://files.pythonhosted.org/packages/6f/07/c67ad1724b8e14e2b4c8cca04b15da158733ac60136879131db05dda7c30/tiktoken-0.9.0-cp311-cp311-win_amd64.whl", hash = "sha256:11a20e67fdf58b0e2dea7b8654a288e481bb4fc0289d3ad21291f8d0849915fb", size = 893895 },
{ url = "https://files.pythonhosted.org/packages/cf/e5/21ff33ecfa2101c1bb0f9b6df750553bd873b7fb532ce2cb276ff40b197f/tiktoken-0.9.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:e88f121c1c22b726649ce67c089b90ddda8b9662545a8aeb03cfef15967ddd03", size = 1065073 },
{ url = "https://files.pythonhosted.org/packages/8e/03/a95e7b4863ee9ceec1c55983e4cc9558bcfd8f4f80e19c4f8a99642f697d/tiktoken-0.9.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a6600660f2f72369acb13a57fb3e212434ed38b045fd8cc6cdd74947b4b5d210", size = 1008075 },
{ url = "https://files.pythonhosted.org/packages/40/10/1305bb02a561595088235a513ec73e50b32e74364fef4de519da69bc8010/tiktoken-0.9.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:95e811743b5dfa74f4b227927ed86cbc57cad4df859cb3b643be797914e41794", size = 1140754 },
{ url = "https://files.pythonhosted.org/packages/1b/40/da42522018ca496432ffd02793c3a72a739ac04c3794a4914570c9bb2925/tiktoken-0.9.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99376e1370d59bcf6935c933cb9ba64adc29033b7e73f5f7569f3aad86552b22", size = 1196678 },
{ url = "https://files.pythonhosted.org/packages/5c/41/1e59dddaae270ba20187ceb8aa52c75b24ffc09f547233991d5fd822838b/tiktoken-0.9.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:badb947c32739fb6ddde173e14885fb3de4d32ab9d8c591cbd013c22b4c31dd2", size = 1259283 },
{ url = "https://files.pythonhosted.org/packages/5b/64/b16003419a1d7728d0d8c0d56a4c24325e7b10a21a9dd1fc0f7115c02f0a/tiktoken-0.9.0-cp312-cp312-win_amd64.whl", hash = "sha256:5a62d7a25225bafed786a524c1b9f0910a1128f4232615bf3f8257a73aaa3b16", size = 894897 },
]
[[package]]