paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-05-21 12:52:13 -05:00
Code Issues Packages Projects Releases Wiki Activity

Just use the built-in ollama LLM class of course

Browse Source
This commit is contained in:
shamoon 2025-04-25 12:01:23 -07:00
parent 741e9a5f82
commit b223d30c6c
No known key found for this signature in database
6 changed files with 38 additions and 379 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
pyproject.toml
View File

@ -48,8 +48,11 @@ dependencies = [
"inotifyrecursive~=0.3",
"jinja2~=3.1.5",
"langdetect~=1.0.9",
"llama-index>=0.12.33",
"llama-index-core>=0.12.33.post1",
"llama-index-embeddings-huggingface>=0.5.3",
"llama-index-embeddings-openai>=0.3.1",
"llama-index-llms-ollama>=0.5.4",
"llama-index-llms-openai>=0.3.38",
"llama-index-vector-stores-faiss>=0.3",
"nltk~=3.9.1",
"ocrmypdf~=16.10.0",

3
src/paperless/ai/chat.py
View File

@ -70,5 +70,4 @@ def stream_chat_with_documents(query_str: str, documents: list[Document]):
response_stream = query_engine.query(prompt)
for chunk in response_stream.response_gen:
yield chunk.text
yield from response_stream.response_gen

5
src/paperless/ai/client.py
View File

@ -1,9 +1,9 @@
import logging
from llama_index.core.llms import ChatMessage
from llama_index.llms.ollama import Ollama
from llama_index.llms.openai import OpenAI
from paperless.ai.llms import OllamaLLM
from paperless.config import AIConfig
logger = logging.getLogger("paperless.ai.client")
@ -20,9 +20,10 @@ class AIClient:
def get_llm(self):
if self.settings.llm_backend == "ollama":
return OllamaLLM(
return Ollama(
model=self.settings.llm_model or "llama3",
base_url=self.settings.llm_url or "http://localhost:11434",
request_timeout=120,
)
elif self.settings.llm_backend == "openai":
return OpenAI(

113
src/paperless/ai/llms.py
View File

@ -1,113 +0,0 @@
import json
import httpx
from llama_index.core.base.llms.types import ChatMessage
from llama_index.core.base.llms.types import ChatResponse
from llama_index.core.base.llms.types import ChatResponseGen
from llama_index.core.base.llms.types import CompletionResponse
from llama_index.core.base.llms.types import CompletionResponseGen
from llama_index.core.base.llms.types import LLMMetadata
from llama_index.core.llms.llm import LLM
from llama_index.core.prompts import SelectorPromptTemplate
from pydantic import Field
class OllamaLLM(LLM):
model: str = Field(default="llama3")
base_url: str = Field(default="http://localhost:11434")
@property
def metadata(self) -> LLMMetadata:
return LLMMetadata(
model_name=self.model,
is_chat_model=False,
context_window=4096,
num_output=512,
is_function_calling_model=False,
)
def complete(self, prompt: str, **kwargs) -> CompletionResponse:
with httpx.Client(timeout=120.0) as client:
response = client.post(
f"{self.base_url}/api/generate",
json={
"model": self.model,
"prompt": prompt,
"stream": False,
},
)
response.raise_for_status()
data = response.json()
return CompletionResponse(text=data["response"])
def stream(self, prompt: str, **kwargs) -> CompletionResponseGen:
return self.stream_complete(prompt, **kwargs)
def stream_complete(
self,
prompt: SelectorPromptTemplate,
**kwargs,
) -> CompletionResponseGen:
headers = {"Content-Type": "application/json"}
data = {
"model": self.model,
"prompt": prompt.format(llm=self),
"stream": True,
}
with httpx.stream(
"POST",
f"{self.base_url}/api/generate",
headers=headers,
json=data,
timeout=60.0,
) as response:
response.raise_for_status()
for line in response.iter_lines():
if not line.strip():
continue
chunk = json.loads(line)
if "response" in chunk:
yield CompletionResponse(text=chunk["response"])
def chat(
self,
messages: list[ChatMessage],
**kwargs,
) -> ChatResponse: # pragma: no cover
raise NotImplementedError("chat not supported")
def stream_chat(
self,
messages: list[ChatMessage],
**kwargs,
) -> ChatResponseGen: # pragma: no cover
raise NotImplementedError("stream_chat not supported")
async def achat(
self,
messages: list[ChatMessage],
**kwargs,
) -> ChatResponse: # pragma: no cover
raise NotImplementedError("async chat not supported")
async def astream_chat(
self,
messages: list[ChatMessage],
**kwargs,
) -> ChatResponseGen: # pragma: no cover
raise NotImplementedError("async stream_chat not supported")
async def acomplete(
self,
prompt: str,
**kwargs,
) -> CompletionResponse: # pragma: no cover
raise NotImplementedError("async complete not supported")
async def astream_complete(
self,
prompt: str,
**kwargs,
) -> CompletionResponseGen: # pragma: no cover
raise NotImplementedError("async stream_complete not supported")

5
src/paperless/tests/test_ai_client.py
View File

@ -17,8 +17,8 @@ def mock_ai_config():
@pytest.fixture
def mock_ollama_llm():
with patch("paperless.ai.client.OllamaLLM") as MockOllamaLLM:
yield MockOllamaLLM
with patch("paperless.ai.client.Ollama") as MockOllama:
yield MockOllama
@pytest.fixture
@ -37,6 +37,7 @@ def test_get_llm_ollama(mock_ai_config, mock_ollama_llm):
mock_ollama_llm.assert_called_once_with(
model="test_model",
base_url="http://test-url",
request_timeout=120,
)
assert client.llm == mock_ollama_llm.return_value

286
uv.lock generated
View File

@ -239,19 +239,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/04/4a/7fdca29d1db62f5f5c3446bf8f668beacdb0b5a8aff4247574ddfddc6bcd/banks-2.1.2-py3-none-any.whl", hash = "sha256:7fba451069f6bea376483b8136a0f29cb1e6883133626d00e077e20a3d102c0e", size = 28064 },
]
[[package]]
name = "beautifulsoup4"
version = "4.13.4"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "soupsieve", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/d8/e4/0c4c39e18fd76d6a628d4dd8da40543d136ce2d1752bd6eeeab0791f4d6b/beautifulsoup4-4.13.4.tar.gz", hash = "sha256:dbb3c4e1ceae6aefebdaf2423247260cd062430a410e38c66f2baa50a8437195", size = 621067 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/50/cd/30110dc0ffcf3b131156077b90e9f60ed75711223f306da4db08eff8403b/beautifulsoup4-4.13.4-py3-none-any.whl", hash = "sha256:9bbbb14bfde9d79f38b8cd5f8c7c85f4b8f2523190ebed90e950a8dea4cb1c4b", size = 187285 },
]
[[package]]
name = "billiard"
version = "4.2.1"
@ -1857,88 +1844,6 @@ dependencies = [
]
sdist = { url = "https://files.pythonhosted.org/packages/0e/72/a3add0e4eec4eb9e2569554f7c70f4a3c27712f40e3284d483e88094cc0e/langdetect-1.0.9.tar.gz", hash = "sha256:cbc1fef89f8d062739774bd51eda3da3274006b3661d199c2655f6b3f6d605a0", size = 981474 }
[[package]]
name = "llama-cloud"
version = "0.1.18"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "certifi", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "httpx", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "pydantic", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/e3/fd/3c68299b531ba5b2ff9698045d0b43ba32b4cb46c3b778e5d7dd2c028e47/llama_cloud-0.1.18.tar.gz", hash = "sha256:65cb88b1cb1a3a0e63e4438e8c8a2e6013dfdafbb4201d274c0459e5d04fb328", size = 93191 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/70/75/a640840f28e1e99837242cfbefde3b19d27c269acb206394a735b5e109ce/llama_cloud-0.1.18-py3-none-any.whl", hash = "sha256:5842722a0c3033afa930b4a50d43e6f1e77ff1dab12383a769dc51a15fb87c9b", size = 253117 },
]
[[package]]
name = "llama-cloud-services"
version = "0.6.15"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "click", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-cloud", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "platformdirs", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "pydantic", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "python-dotenv", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/56/4e/da311d13340d22705d6ae48732c78a580039f132dfcaa68a7063b066c38c/llama_cloud_services-0.6.15.tar.gz", hash = "sha256:912799d9cdcf48074145c6781f40a6dd7dadb6344ecb30b715407db85a0e675e", size = 31701 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/f5/0d/88805be6a13b368c9e7a2b2cede60fd0298e0e3abc9a6a6923d414c1ab14/llama_cloud_services-0.6.15-py3-none-any.whl", hash = "sha256:c4e24dd41f2cde17eeba7750d41cc70fe26e1179c03ae832122d762572e53de6", size = 36676 },
]
[[package]]
name = "llama-index"
version = "0.12.33"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "llama-index-agent-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-cli", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-embeddings-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-indices-managed-llama-cloud", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-llms-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-multi-modal-llms-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-program-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-question-gen-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-readers-file", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-readers-llama-parse", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "nltk", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/4e/b1/b3945f51e3733d7d083f4f2139c7a6670264f88263ab33f6d4614f867d8c/llama_index-0.12.33.tar.gz", hash = "sha256:038da75552784f0e22379b6a816f36f74b31b28c6cbca063222c5f4225a2b497", size = 7886 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/29/53/953c33438b20b9c6b25c0b892e9ec7984c8ab6e6cb796987bded8ca56a6a/llama_index-0.12.33-py3-none-any.whl", hash = "sha256:300261e64174afe355afcf06037c5c38c4a5b17caf75db66664cd9c7a5b9dd17", size = 6982 },
]
[[package]]
name = "llama-index-agent-openai"
version = "0.4.6"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-llms-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/f2/bd/7984c6964c2742991e6309e678375a7e6adef99e19e67ad95cbbb67b45a5/llama_index_agent_openai-0.4.6.tar.gz", hash = "sha256:4f66c1731836ab66c4b441255a95f33a51743e4993b8aa9daf430cb31aa7d48e", size = 10871 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/8a/1f/a0e2eed0417b1f3b6a51da159eb57640f0501e74fd502f83a254b3a55054/llama_index_agent_openai-0.4.6-py3-none-any.whl", hash = "sha256:4103e479c874cb3426aa59a13f91b6e2dc6b350c51457966631f8bdaf9a6a8e8", size = 13358 },
]
[[package]]
name = "llama-index-cli"
version = "0.4.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-embeddings-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-llms-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/4e/01/2155f7b830b84d09b98e6fd8094b333d39b0a0e4d2d28c9d2b0b6262757d/llama_index_cli-0.4.1.tar.gz", hash = "sha256:3f97f1f8f5f401dfb5b6bc7170717c176dcd981538017430073ef12ffdcbddfa", size = 25054 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/ae/fa/2ee58764d733e9b5d61036ba6c8c96adcdb567ea16a62c247519fbf34c13/llama_index_cli-0.4.1-py3-none-any.whl", hash = "sha256:6dfc931aea5b90c256e476b48dfac76f48fb2308fdf656bb02ee1e4f2cab8b06", size = 28493 },
]
[[package]]
name = "llama-index-core"
version = "0.12.33.post1"
@ -2001,16 +1906,16 @@ wheels = [
]
[[package]]
name = "llama-index-indices-managed-llama-cloud"
version = "0.6.11"
name = "llama-index-llms-ollama"
version = "0.5.4"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "llama-cloud", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "ollama", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/75/bc/d1a9013b117005a782a253bce16a1d1022349b85fe6206395376477ce6c6/llama_index_indices_managed_llama_cloud-0.6.11.tar.gz", hash = "sha256:925532f760cd2ebb2594828da311adac3d54cd2cae3dff2908491eebb2b8bd0f", size = 12703 }
sdist = { url = "https://files.pythonhosted.org/packages/36/05/bd6a1006d93566a65cb5ef8318bca8695a9a7cfc6064c1bd218aae3a5ded/llama_index_llms_ollama-0.5.4.tar.gz", hash = "sha256:e5e7e7a4e65478c762906d08f594647d8148ffdc32ae908d56b73c0df8ea04f2", size = 8218 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/7e/f4/5decd79fd7f2f0e44c5689af62497447e86832e876b7dad11903259de5f9/llama_index_indices_managed_llama_cloud-0.6.11-py3-none-any.whl", hash = "sha256:64e82e2ac178cd3721b76c0817edd57e05a3bd877c412b4148d3abbdeea62d59", size = 14272 },
{ url = "https://files.pythonhosted.org/packages/33/1d/f000f50525dff87e6a78d7d7623720fdfc14b95a04b25e2bc4e936af2907/llama_index_llms_ollama-0.5.4-py3-none-any.whl", hash = "sha256:203688429a99454ae261877dd48f68f65374edf92ba25796a6a8a2346fd005f0", size = 7790 },
]
[[package]]
@ -2026,76 +1931,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/e4/e1/1c185e22ca1fd1ac813d225be046c4223dbe2fdf64d90a6e86608e6d17ad/llama_index_llms_openai-0.3.38-py3-none-any.whl", hash = "sha256:d724b809d5e81e15cd1c3def65f023c4c74f2a097e542e5c002793ffbaa33a96", size = 23839 },
]
[[package]]
name = "llama-index-multi-modal-llms-openai"
version = "0.4.3"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-llms-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/1a/9a/e3ab972880fc08d39475a0c7969b1a16ece58fe7f41ab8645f8342d57634/llama_index_multi_modal_llms_openai-0.4.3.tar.gz", hash = "sha256:5e6ca54069d3d18c2f5f7ca34f3720fba1d1b9126482ad38feb0c858f4feb63b", size = 5094 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/75/90/7a5a44959192b739718618d6fbfb5be8d21909dbd81865b9d4bb45a8bc89/llama_index_multi_modal_llms_openai-0.4.3-py3-none-any.whl", hash = "sha256:1ceb42716472ac8bd5130afa29b793869d367946aedd02e48a3b03184e443ad1", size = 5870 },
]
[[package]]
name = "llama-index-program-openai"
version = "0.3.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "llama-index-agent-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-llms-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/7a/b8/24f1103106bfeed04f0e33b587863345c2d7fad001828bb02844a5427fbc/llama_index_program_openai-0.3.1.tar.gz", hash = "sha256:6039a6cdbff62c6388c07e82a157fe2edd3bbef0c5adf292ad8546bf4ec75b82", size = 4818 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/00/59/3f31171c30a08c8ba21155d5241ba174630e57cf43b03d97fd77bf565b51/llama_index_program_openai-0.3.1-py3-none-any.whl", hash = "sha256:93646937395dc5318fd095153d2f91bd632b25215d013d14a87c088887d205f9", size = 5318 },
]
[[package]]
name = "llama-index-question-gen-openai"
version = "0.3.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-llms-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-program-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/4e/47/c57392e2fb00c0f596f912e7977e3c639ac3314f2aed5d4ac733baa367f1/llama_index_question_gen_openai-0.3.0.tar.gz", hash = "sha256:efd3b468232808e9d3474670aaeab00e41b90f75f52d0c9bfbf11207e0963d62", size = 2608 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/7c/2c/765b0dfc2c988bbea267e236c836d7a96c60a20df76d842e43e17401f800/llama_index_question_gen_openai-0.3.0-py3-none-any.whl", hash = "sha256:9b60ec114273a63b50349948666e5744a8f58acb645824e07c979041e8fec598", size = 2899 },
]
[[package]]
name = "llama-index-readers-file"
version = "0.4.7"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "beautifulsoup4", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "pandas", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "pypdf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "striprtf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/a9/18/aa079089644ac9adbe11754e5624390cc9147ce0606e2cd3dfb7b392a5ee/llama_index_readers_file-0.4.7.tar.gz", hash = "sha256:89a765238a106af0f1e31ab8d4cb3ee33ac897080285bcce59101b420265ebd1", size = 23793 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/53/8c/d40d3dbee8012b320aacfdeb131e834bc37f3cb2b978a514d2ff5c4ffd47/llama_index_readers_file-0.4.7-py3-none-any.whl", hash = "sha256:dff86f9b6079bddad37896f26756b508be5a052096ced34c9917b76646cf0c02", size = 40834 },
]
[[package]]
name = "llama-index-readers-llama-parse"
version = "0.4.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-parse", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/35/30/4611821286f82ba7b5842295607baa876262db86f88b87d83595eed172bf/llama_index_readers_llama_parse-0.4.0.tar.gz", hash = "sha256:e99ec56f4f8546d7fda1a7c1ae26162fb9acb7ebcac343b5abdb4234b4644e0f", size = 2472 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/68/4f/e30d4257fe9e4224f5612b77fe99aaceddae411b2e74ca30534491de3e6f/llama_index_readers_llama_parse-0.4.0-py3-none-any.whl", hash = "sha256:574e48386f28d2c86c3f961ca4a4906910312f3400dd0c53014465bfbc6b32bf", size = 2472 },
]
[[package]]
name = "llama-index-vector-stores-faiss"
version = "0.3.0"
@ -2108,18 +1943,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/21/16/d3f512f47d40a27ee1c75ce86faa91004de9c20202ca376fe35bc92ba413/llama_index_vector_stores_faiss-0.3.0-py3-none-any.whl", hash = "sha256:2148163dba1222c855bd367a7b796bc35d46dc2e77d57bafd321ba14aac00177", size = 3868 },
]
[[package]]
name = "llama-parse"
version = "0.6.12"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "llama-cloud-services", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/c4/27/8014c38cab1e9664153157d3c8693af726c0f7ae0c93adaebace5da688d7/llama_parse-0.6.12.tar.gz", hash = "sha256:c99593fb955c338a69e64a2ec449e09753afe6dcff239ab050989fda74839867", size = 3673 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/ac/ca/71c9367d3e89d61da2462f535dea1a3a09d4a4085b96f2c9ef5c38864820/llama_parse-0.6.12-py3-none-any.whl", hash = "sha256:2dd1c74b0cba1a2bc300286f6b91a650f6ddc396acfce3497ba3d72d43c53fac", size = 4853 },
]
[[package]]
name = "lxml"
version = "5.3.1"
@ -2813,6 +2636,19 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/33/47/10058f54f593f5e618a6796fc3e8dc3e19536128f832e2d3d6e4943e9834/ocrmypdf-16.10.0-py3-none-any.whl", hash = "sha256:5093b9b058e7278b17c0b0978eb5175063b7a5511e3b9068257ece063d91ce8f", size = 162336 },
]
[[package]]
name = "ollama"
version = "0.4.8"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "httpx", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "pydantic", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/e2/64/709dc99030f8f46ec552f0a7da73bbdcc2da58666abfec4742ccdb2e800e/ollama-0.4.8.tar.gz", hash = "sha256:1121439d49b96fa8339842965d0616eba5deb9f8c790786cdf4c0b3df4833802", size = 12972 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/33/3f/164de150e983b3a16e8bf3d4355625e51a357e7b3b1deebe9cc1f7cb9af8/ollama-0.4.8-py3-none-any.whl", hash = "sha256:04312af2c5e72449aaebac4a2776f52ef010877c554103419d3f36066fe8af4c", size = 13325 },
]
[[package]]
name = "openai"
version = "1.76.0"
@ -2850,50 +2686,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/90/96/04b8e52da071d28f5e21a805b19cb9390aa17a47462ac87f5e2696b9566d/paginate-0.5.7-py2.py3-none-any.whl", hash = "sha256:b885e2af73abcf01d9559fd5216b57ef722f8c42affbb63942377668e35c7591", size = 13746 },
]
[[package]]
name = "pandas"
version = "2.2.3"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "numpy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "python-dateutil", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "pytz", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "tzdata", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/9c/d6/9f8431bacc2e19dca897724cd097b1bb224a6ad5433784a44b587c7c13af/pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667", size = 4399213 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/aa/70/c853aec59839bceed032d52010ff5f1b8d87dc3114b762e4ba2727661a3b/pandas-2.2.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:1948ddde24197a0f7add2bdc4ca83bf2b1ef84a1bc8ccffd95eda17fd836ecb5", size = 12580827 },
{ url = "https://files.pythonhosted.org/packages/99/f2/c4527768739ffa4469b2b4fff05aa3768a478aed89a2f271a79a40eee984/pandas-2.2.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:381175499d3802cde0eabbaf6324cce0c4f5d52ca6f8c377c29ad442f50f6348", size = 11303897 },
{ url = "https://files.pythonhosted.org/packages/ed/12/86c1747ea27989d7a4064f806ce2bae2c6d575b950be087837bdfcabacc9/pandas-2.2.3-cp310-cp310-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d9c45366def9a3dd85a6454c0e7908f2b3b8e9c138f5dc38fed7ce720d8453ed", size = 66480908 },
{ url = "https://files.pythonhosted.org/packages/44/50/7db2cd5e6373ae796f0ddad3675268c8d59fb6076e66f0c339d61cea886b/pandas-2.2.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:86976a1c5b25ae3f8ccae3a5306e443569ee3c3faf444dfd0f41cda24667ad57", size = 13064210 },
{ url = "https://files.pythonhosted.org/packages/61/61/a89015a6d5536cb0d6c3ba02cebed51a95538cf83472975275e28ebf7d0c/pandas-2.2.3-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:b8661b0238a69d7aafe156b7fa86c44b881387509653fdf857bebc5e4008ad42", size = 16754292 },
{ url = "https://files.pythonhosted.org/packages/ce/0d/4cc7b69ce37fac07645a94e1d4b0880b15999494372c1523508511b09e40/pandas-2.2.3-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:37e0aced3e8f539eccf2e099f65cdb9c8aa85109b0be6e93e2baff94264bdc6f", size = 14416379 },
{ url = "https://files.pythonhosted.org/packages/a8/44/d9502bf0ed197ba9bf1103c9867d5904ddcaf869e52329787fc54ed70cc8/pandas-2.2.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:66108071e1b935240e74525006034333f98bcdb87ea116de573a6a0dccb6c039", size = 12602222 },
{ url = "https://files.pythonhosted.org/packages/52/11/9eac327a38834f162b8250aab32a6781339c69afe7574368fffe46387edf/pandas-2.2.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7c2875855b0ff77b2a64a0365e24455d9990730d6431b9e0ee18ad8acee13dbd", size = 11321274 },
{ url = "https://files.pythonhosted.org/packages/45/fb/c4beeb084718598ba19aa9f5abbc8aed8b42f90930da861fcb1acdb54c3a/pandas-2.2.3-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:cd8d0c3be0515c12fed0bdbae072551c8b54b7192c7b1fda0ba56059a0179698", size = 15579836 },
{ url = "https://files.pythonhosted.org/packages/cd/5f/4dba1d39bb9c38d574a9a22548c540177f78ea47b32f99c0ff2ec499fac5/pandas-2.2.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c124333816c3a9b03fbeef3a9f230ba9a737e9e5bb4060aa2107a86cc0a497fc", size = 13058505 },
{ url = "https://files.pythonhosted.org/packages/b9/57/708135b90391995361636634df1f1130d03ba456e95bcf576fada459115a/pandas-2.2.3-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:63cc132e40a2e084cf01adf0775b15ac515ba905d7dcca47e9a251819c575ef3", size = 16744420 },
{ url = "https://files.pythonhosted.org/packages/86/4a/03ed6b7ee323cf30404265c284cee9c65c56a212e0a08d9ee06984ba2240/pandas-2.2.3-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:29401dbfa9ad77319367d36940cd8a0b3a11aba16063e39632d98b0e931ddf32", size = 14440457 },
{ url = "https://files.pythonhosted.org/packages/17/a3/fb2734118db0af37ea7433f57f722c0a56687e14b14690edff0cdb4b7e58/pandas-2.2.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b1d432e8d08679a40e2a6d8b2f9770a5c21793a6f9f47fdd52c5ce1948a5a8a9", size = 12529893 },
{ url = "https://files.pythonhosted.org/packages/e1/0c/ad295fd74bfac85358fd579e271cded3ac969de81f62dd0142c426b9da91/pandas-2.2.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a5a1595fe639f5988ba6a8e5bc9649af3baf26df3998a0abe56c02609392e0a4", size = 11363475 },
{ url = "https://files.pythonhosted.org/packages/c6/2a/4bba3f03f7d07207481fed47f5b35f556c7441acddc368ec43d6643c5777/pandas-2.2.3-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:5de54125a92bb4d1c051c0659e6fcb75256bf799a732a87184e5ea503965bce3", size = 15188645 },
{ url = "https://files.pythonhosted.org/packages/38/f8/d8fddee9ed0d0c0f4a2132c1dfcf0e3e53265055da8df952a53e7eaf178c/pandas-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fffb8ae78d8af97f849404f21411c95062db1496aeb3e56f146f0355c9989319", size = 12739445 },
{ url = "https://files.pythonhosted.org/packages/20/e8/45a05d9c39d2cea61ab175dbe6a2de1d05b679e8de2011da4ee190d7e748/pandas-2.2.3-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6dfcb5ee8d4d50c06a51c2fffa6cff6272098ad6540aed1a76d15fb9318194d8", size = 16359235 },
{ url = "https://files.pythonhosted.org/packages/1d/99/617d07a6a5e429ff90c90da64d428516605a1ec7d7bea494235e1c3882de/pandas-2.2.3-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:062309c1b9ea12a50e8ce661145c6aab431b1e99530d3cd60640e255778bd43a", size = 14056756 },
{ url = "https://files.pythonhosted.org/packages/64/22/3b8f4e0ed70644e85cfdcd57454686b9057c6c38d2f74fe4b8bc2527214a/pandas-2.2.3-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f00d1345d84d8c86a63e476bb4955e46458b304b9575dcf71102b5c705320015", size = 12477643 },
{ url = "https://files.pythonhosted.org/packages/e4/93/b3f5d1838500e22c8d793625da672f3eec046b1a99257666c94446969282/pandas-2.2.3-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:3508d914817e153ad359d7e069d752cdd736a247c322d932eb89e6bc84217f28", size = 11281573 },
{ url = "https://files.pythonhosted.org/packages/f5/94/6c79b07f0e5aab1dcfa35a75f4817f5c4f677931d4234afcd75f0e6a66ca/pandas-2.2.3-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:22a9d949bfc9a502d320aa04e5d02feab689d61da4e7764b62c30b991c42c5f0", size = 15196085 },
{ url = "https://files.pythonhosted.org/packages/e8/31/aa8da88ca0eadbabd0a639788a6da13bb2ff6edbbb9f29aa786450a30a91/pandas-2.2.3-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f3a255b2c19987fbbe62a9dfd6cff7ff2aa9ccab3fc75218fd4b7530f01efa24", size = 12711809 },
{ url = "https://files.pythonhosted.org/packages/ee/7c/c6dbdb0cb2a4344cacfb8de1c5808ca885b2e4dcfde8008266608f9372af/pandas-2.2.3-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:800250ecdadb6d9c78eae4990da62743b857b470883fa27f652db8bdde7f6659", size = 16356316 },
{ url = "https://files.pythonhosted.org/packages/57/b7/8b757e7d92023b832869fa8881a992696a0bfe2e26f72c9ae9f255988d42/pandas-2.2.3-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6374c452ff3ec675a8f46fd9ab25c4ad0ba590b71cf0656f8b6daa5202bca3fb", size = 14022055 },
{ url = "https://files.pythonhosted.org/packages/76/a3/a5d88146815e972d40d19247b2c162e88213ef51c7c25993942c39dbf41d/pandas-2.2.3-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:3b71f27954685ee685317063bf13c7709a7ba74fc996b84fc6821c59b0f06468", size = 12615650 },
{ url = "https://files.pythonhosted.org/packages/9c/8c/f0fd18f6140ddafc0c24122c8a964e48294acc579d47def376fef12bcb4a/pandas-2.2.3-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:38cf8125c40dae9d5acc10fa66af8ea6fdf760b2714ee482ca691fc66e6fcb18", size = 11290177 },
{ url = "https://files.pythonhosted.org/packages/ed/f9/e995754eab9c0f14c6777401f7eece0943840b7a9fc932221c19d1abee9f/pandas-2.2.3-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:ba96630bc17c875161df3818780af30e43be9b166ce51c9a18c1feae342906c2", size = 14651526 },
{ url = "https://files.pythonhosted.org/packages/25/b0/98d6ae2e1abac4f35230aa756005e8654649d305df9a28b16b9ae4353bff/pandas-2.2.3-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1db71525a1538b30142094edb9adc10be3f3e176748cd7acc2240c2f2e5aa3a4", size = 11871013 },
{ url = "https://files.pythonhosted.org/packages/cc/57/0f72a10f9db6a4628744c8e8f0df4e6e21de01212c7c981d31e50ffc8328/pandas-2.2.3-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:15c0e1e02e93116177d29ff83e8b1619c93ddc9c49083f237d4312337a61165d", size = 15711620 },
{ url = "https://files.pythonhosted.org/packages/ab/5f/b38085618b950b79d2d9164a711c52b10aefc0ae6833b96f626b7021b2ed/pandas-2.2.3-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:ad5b65698ab28ed8d7f18790a0dc58005c7629f227be9ecc1072aa74c0c1d43a", size = 13098436 },
]
[[package]]
name = "paperless-ngx"
version = "2.16.1"
@ -2930,8 +2722,11 @@ dependencies = [
{ name = "inotifyrecursive", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "jinja2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "langdetect", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-embeddings-huggingface", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-embeddings-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-llms-ollama", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-llms-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "llama-index-vector-stores-faiss", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "nltk", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
{ name = "ocrmypdf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@ -3067,9 +2862,12 @@ requires-dist = [
{ name = "inotifyrecursive", specifier = "~=0.3" },
{ name = "jinja2", specifier = "~=3.1.5" },
{ name = "langdetect", specifier = "~=1.0.9" },
{ name = "llama-index", specifier = ">=0.12.33" },
{ name = "llama-index-core", specifier = ">=0.12.33.post1" },
{ name = "llama-index-embeddings-huggingface", specifier = ">=0.5.3" },
{ name = "llama-index-vector-stores-faiss", specifier = ">=0.3.0" },
{ name = "llama-index-embeddings-openai", specifier = ">=0.3.1" },
{ name = "llama-index-llms-ollama", specifier = ">=0.5.4" },
{ name = "llama-index-llms-openai", specifier = ">=0.3.38" },
{ name = "llama-index-vector-stores-faiss", specifier = ">=0.3" },
{ name = "mysqlclient", marker = "extra == 'mariadb'", specifier = "~=2.2.7" },
{ name = "nltk", specifier = "~=3.9.1" },
{ name = "ocrmypdf", specifier = "~=16.10.0" },
@ -3714,18 +3512,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/ca/d7/eb76863d2060dcbe7c7e6cccfd95ac02ea0b9acc37745a0d99ff6457aefb/pyOpenSSL-25.0.0-py3-none-any.whl", hash = "sha256:424c247065e46e76a37411b9ab1782541c23bb658bf003772c3405fbaa128e90", size = 56453 },
]
[[package]]
name = "pypdf"
version = "5.4.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "typing-extensions", marker = "(python_full_version < '3.11' and sys_platform == 'darwin') or (python_full_version < '3.11' and sys_platform == 'linux')" },
]
sdist = { url = "https://files.pythonhosted.org/packages/f9/43/4026f6ee056306d0e0eb04fcb9f2122a0f1a5c57ad9dc5e0d67399e47194/pypdf-5.4.0.tar.gz", hash = "sha256:9af476a9dc30fcb137659b0dec747ea94aa954933c52cf02ee33e39a16fe9175", size = 5012492 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/0b/27/d83f8f2a03ca5408dc2cc84b49c0bf3fbf059398a6a2ea7c10acfe28859f/pypdf-5.4.0-py3-none-any.whl", hash = "sha256:db994ab47cadc81057ea1591b90e5b543e2b7ef2d0e31ef41a9bfe763c119dab", size = 302306 },
]
[[package]]
name = "pytest"
version = "8.3.4"
@ -4517,15 +4303,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235 },
]
[[package]]
name = "soupsieve"
version = "2.7"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/3f/f4/4a80cd6ef364b2e8b65b15816a843c0980f7a5a2b4dc701fc574952aa19f/soupsieve-2.7.tar.gz", hash = "sha256:ad282f9b6926286d2ead4750552c8a6142bc4c783fd66b0293547c8fe6ae126a", size = 103418 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/e7/9c/0e6afc12c269578be5c0c1c9f4b49a8d32770a080260c333ac04cc1c832d/soupsieve-2.7-py3-none-any.whl", hash = "sha256:6e60cc5c1ffaf1cebcc12e8188320b72071e922c2e897f737cadce79ad5d30c4", size = 36677 },
]
[[package]]
name = "sqlalchemy"
version = "2.0.40"
@ -4577,15 +4354,6 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/a9/5c/bfd6bd0bf979426d405cc6e71eceb8701b148b16c21d2dc3c261efc61c7b/sqlparse-0.5.3-py3-none-any.whl", hash = "sha256:cf2196ed3418f3ba5de6af7e82c694a9fbdbfecccdfc72e281548517081f16ca", size = 44415 },
]
[[package]]
name = "striprtf"
version = "0.0.26"
source = { registry = "https://pypi.org/simple" }
sdist = { url = "https://files.pythonhosted.org/packages/25/20/3d419008265346452d09e5dadfd5d045b64b40d8fc31af40588e6c76997a/striprtf-0.0.26.tar.gz", hash = "sha256:fdb2bba7ac440072d1c41eab50d8d74ae88f60a8b6575c6e2c7805dc462093aa", size = 6258 }
wheels = [
{ url = "https://files.pythonhosted.org/packages/a3/cf/0fea4f4ba3fc2772ac2419278aa9f6964124d4302117d61bc055758e000c/striprtf-0.0.26-py3-none-any.whl", hash = "sha256:8c8f9d32083cdc2e8bfb149455aa1cc5a4e0a035893bedc75db8b73becb3a1bb", size = 6914 },
]
[[package]]
name = "sympy"
version = "1.13.3"