amorfo77/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2026-04-29 03:19:26 +00:00
Code Issues Projects Releases Wiki Activity

Enhancement (dev): Use OpenAI-like backend (#12668)

Browse Source
This commit is contained in:
shamoon
2026-04-28 10:06:59 -07:00
committed by GitHub
parent 2f8f126223
commit 69cb4d06c6
17 changed files with 136 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
docs/configuration.md
View File

@@ -2014,49 +2014,57 @@ suggestions. This setting is required to be set to true in order to use the AI f
#### [`PAPERLESS_AI_LLM_EMBEDDING_BACKEND=<str>`](#PAPERLESS_AI_LLM_EMBEDDING_BACKEND) {#PAPERLESS_AI_LLM_EMBEDDING_BACKEND}
: The embedding backend to use for RAG. This can be either "openai" or "huggingface".
: The embedding backend to use for RAG. This can be either "openai-like" or "huggingface". The
"openai-like" backend uses an OpenAI-compatible embeddings API.
Defaults to None.
#### [`PAPERLESS_AI_LLM_EMBEDDING_MODEL=<str>`](#PAPERLESS_AI_LLM_EMBEDDING_MODEL) {#PAPERLESS_AI_LLM_EMBEDDING_MODEL}
: The model to use for the embedding backend for RAG. This can be set to any of the embedding models supported by the current embedding backend. If not supplied, defaults to "text-embedding-3-small" for OpenAI and "sentence-transformers/all-MiniLM-L6-v2" for Huggingface.
: The model to use for the embedding backend for RAG. This can be set to any of the embedding
models supported by the current embedding backend. If not supplied, defaults to
"text-embedding-3-small" for the OpenAI-compatible backend and
"sentence-transformers/all-MiniLM-L6-v2" for Huggingface.
Defaults to None.
#### [`PAPERLESS_AI_LLM_BACKEND=<str>`](#PAPERLESS_AI_LLM_BACKEND) {#PAPERLESS_AI_LLM_BACKEND}
: The AI backend to use. This can be either "openai" or "ollama". If set to "ollama", the AI
features will be run locally on your machine. If set to "openai", the AI features will be run
using the OpenAI API. This setting is required to be set to use the AI features.
: The AI backend to use. This can be either "openai-like" or "ollama". If set to "ollama", the AI
features will be run locally on your machine. If set to "openai-like", the AI features will use
an OpenAI-compatible API endpoint, including OpenAI itself and compatible providers. This
setting is required to be set to use the AI features.
Defaults to None.
!!! note
The OpenAI API is a paid service. You will need to set up an OpenAI account and
will be charged for usage incurred by Paperless-ngx features and your document data
will (of course) be sent to the OpenAI API. Paperless-ngx does not endorse the use of the
OpenAI API in any way.
Remote AI providers may be paid services. If you use a hosted OpenAI-compatible API, you
are responsible for any usage charges incurred by Paperless-ngx features, and your
document data will be sent to the provider you configure.
Refer to the OpenAI terms of service, and use at your own risk.
Paperless-ngx does not endorse any specific provider. Refer to your provider's terms of
service and privacy policy, and use at your own risk.
#### [`PAPERLESS_AI_LLM_MODEL=<str>`](#PAPERLESS_AI_LLM_MODEL) {#PAPERLESS_AI_LLM_MODEL}
: The model to use for the AI backend, i.e. "gpt-3.5-turbo", "gpt-4" or any of the models supported by the
current backend. If not supplied, defaults to "gpt-3.5-turbo" for OpenAI and "llama3.1" for Ollama.
: The model to use for the AI backend, i.e. "gpt-3.5-turbo", "gpt-4" or any of the models supported
by the current backend. If not supplied, defaults to "gpt-3.5-turbo" for the OpenAI-compatible
backend and "llama3.1" for Ollama.
Defaults to None.
#### [`PAPERLESS_AI_LLM_API_KEY=<str>`](#PAPERLESS_AI_LLM_API_KEY) {#PAPERLESS_AI_LLM_API_KEY}
: The API key to use for the AI backend. This is required for the OpenAI backend (optional for others).
: The API key to use for the AI backend. This is typically required for the OpenAI-compatible
backend (optional for others).
Defaults to None.
#### [`PAPERLESS_AI_LLM_ENDPOINT=<str>`](#PAPERLESS_AI_LLM_ENDPOINT) {#PAPERLESS_AI_LLM_ENDPOINT}
: The endpoint / url to use for the AI backend. This is required for the Ollama backend (optional for others).
: The endpoint / url to use for the AI backend. This is required for the Ollama backend and may be
used with the OpenAI-compatible backend to target a custom provider or local gateway.
Defaults to None.

10
docs/usage.md
View File

@@ -302,13 +302,19 @@ Paperless-ngx includes several features that use AI to enhance the document mana
!!! warning
Remember that Paperless-ngx will send document content to the AI provider you have configured, so consider the privacy implications of using these features, especially if using a remote model (e.g. OpenAI), instead of the default local model.
Remember that Paperless-ngx will send document content to the AI provider you have configured,
so consider the privacy implications of using these features, especially if using a remote
model or API provider instead of the default local model.
The AI features work by creating an embedding of the text content and metadata of documents, which is then used for various tasks such as similarity search and question answering. This uses the FAISS vector store.
### AI-Enhanced Suggestions
If enabled, Paperless-ngx can use an AI LLM model to suggest document titles, dates, tags, correspondents and document types for documents. This feature will always be "opt-in" and does not disable the existing classifier-based suggestion system. Currently, both remote (via the OpenAI API) and local (via Ollama) models are supported, see [configuration](configuration.md#ai) for details.
If enabled, Paperless-ngx can use an AI LLM model to suggest document titles, dates, tags,
correspondents and document types for documents. This feature will always be "opt-in" and does not
disable the existing classifier-based suggestion system. Currently, both remote
(via OpenAI-compatible APIs) and local (via Ollama) models are supported, see
[configuration](configuration.md#ai) for details.
### Document Chat

4
pyproject.toml
View File

@@ -53,9 +53,9 @@ dependencies = [
"langdetect~=1.0.9",
"llama-index-core>=0.14.12",
"llama-index-embeddings-huggingface>=0.6.1",
"llama-index-embeddings-openai>=0.5.1",
"llama-index-embeddings-openai-like>=0.2.2",
"llama-index-llms-ollama>=0.9.1",
"llama-index-llms-openai>=0.6.13",
"llama-index-llms-openai-like>=0.7.1",
"llama-index-vector-stores-faiss>=0.5.2",
"nltk~=3.9.1",
"ocrmypdf~=17.4.0",

4
src-ui/src/app/data/paperless-config.ts
View File

@@ -55,12 +55,12 @@ export const ConfigCategory = {
}
export const LLMEmbeddingBackendConfig = {
OPENAI: 'openai',
OPENAI_LIKE: 'openai-like',
HUGGINGFACE: 'huggingface',
}
export const LLMBackendConfig = {
OPENAI: 'openai',
OPENAI_LIKE: 'openai-like',
OLLAMA: 'ollama',
}

3
src/documents/caching.py
View File

@@ -218,7 +218,8 @@ def set_llm_suggestions_cache(
timeout: int = CACHE_50_MINUTES,
) -> None:
"""
Cache LLM-generated suggestions using a backend-specific identifier (e.g. 'openai:gpt-4').
Cache LLM-generated suggestions using a backend-specific identifier
(e.g. 'openai-like:gpt-4').
"""
doc_key = get_suggestion_cache_key(document_id)
cache.set(

2
src/documents/tests/test_api_app_config.py
View File

@@ -848,7 +848,7 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
json.dumps(
{
"ai_enabled": True,
"llm_embedding_backend": "openai",
"llm_embedding_backend": "openai-like",
},
),
content_type="application/json",

4
src/documents/tests/test_api_status.py
View File

@@ -404,7 +404,7 @@ class TestSystemStatus(APITestCase):
THEN:
- The response contains the correct AI status
"""
with override_settings(AI_ENABLED=True, LLM_EMBEDDING_BACKEND="openai"):
with override_settings(AI_ENABLED=True, LLM_EMBEDDING_BACKEND="openai-like"):
self.client.force_login(self.user)
# No tasks found
@@ -431,7 +431,7 @@ class TestSystemStatus(APITestCase):
THEN:
- The response contains the correct AI status
"""
with override_settings(AI_ENABLED=True, LLM_EMBEDDING_BACKEND="openai"):
with override_settings(AI_ENABLED=True, LLM_EMBEDDING_BACKEND="openai-like"):
PaperlessTaskFactory(
task_type=PaperlessTask.TaskType.LLM_INDEX,
trigger_source=PaperlessTask.TriggerSource.SCHEDULED,

6
src/documents/tests/test_views.py
View File

@@ -359,7 +359,7 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
@patch("documents.views.get_ai_document_classification")
@override_settings(
AI_ENABLED=True,
LLM_BACKEND="openai",
LLM_BACKEND="openai-like",
)
def test_suggestions_with_invalid_ai_configuration(
self,
@@ -379,7 +379,9 @@ class TestAISuggestions(DirectoriesMixin, TestCase):
"ai": ["Invalid AI configuration."],
},
)
self.assertIsNone(get_llm_suggestion_cache(self.document.pk, backend="openai"))
self.assertIsNone(
get_llm_suggestion_cache(self.document.pk, backend="openai-like"),
)
def test_invalidate_suggestions_cache(self) -> None:
self.client.force_login(user=self.user)

7
src/paperless/migrations/0005_applicationconfiguration_ai_enabled_and_more.py
View File

@@ -34,7 +34,7 @@ class Migration(migrations.Migration):
name="llm_backend",
field=models.CharField(
blank=True,
choices=[("openai", "OpenAI"), ("ollama", "Ollama")],
choices=[("openai-like", "OpenAI-compatible"), ("ollama", "Ollama")],
max_length=128,
null=True,
verbose_name="Sets the LLM backend",
@@ -45,7 +45,10 @@ class Migration(migrations.Migration):
name="llm_embedding_backend",
field=models.CharField(
blank=True,
choices=[("openai", "OpenAI"), ("huggingface", "Huggingface")],
choices=[
("openai-like", "OpenAI-compatible"),
("huggingface", "Huggingface"),
],
max_length=128,
null=True,
verbose_name="Sets the LLM embedding backend",

4
src/paperless/models.py
View File

@@ -75,7 +75,7 @@ class ColorConvertChoices(models.TextChoices):
class LLMEmbeddingBackend(models.TextChoices):
OPENAI = ("openai", _("OpenAI"))
OPENAI_LIKE = ("openai-like", _("OpenAI-compatible"))
HUGGINGFACE = ("huggingface", _("Huggingface"))
@@ -84,7 +84,7 @@ class LLMBackend(models.TextChoices):
Matches to --llm-backend
"""
OPENAI = ("openai", _("OpenAI"))
OPENAI_LIKE = ("openai-like", _("OpenAI-compatible"))
OLLAMA = ("ollama", _("Ollama"))

4
src/paperless/settings/__init__.py
View File

@@ -1174,9 +1174,9 @@ REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")
AI_ENABLED = get_bool_from_env("PAPERLESS_AI_ENABLED", "NO")
LLM_EMBEDDING_BACKEND = os.getenv(
"PAPERLESS_AI_LLM_EMBEDDING_BACKEND",
) # "huggingface" or "openai"
) # "huggingface" or "openai-like"
LLM_EMBEDDING_MODEL = os.getenv("PAPERLESS_AI_LLM_EMBEDDING_MODEL")
LLM_BACKEND = os.getenv("PAPERLESS_AI_LLM_BACKEND") # "ollama" or "openai"
LLM_BACKEND = os.getenv("PAPERLESS_AI_LLM_BACKEND") # "ollama" or "openai-like"
LLM_MODEL = os.getenv("PAPERLESS_AI_LLM_MODEL")
LLM_API_KEY = os.getenv("PAPERLESS_AI_LLM_API_KEY")
LLM_ENDPOINT = os.getenv("PAPERLESS_AI_LLM_ENDPOINT")

16
src/paperless_ai/client.py
View File

@@ -1,10 +1,12 @@
import logging
from typing import TYPE_CHECKING
from paperless.models import LLMBackend
if TYPE_CHECKING:
from llama_index.core.llms import ChatMessage
from llama_index.llms.ollama import Ollama
from llama_index.llms.openai import OpenAI
from llama_index.llms.openai_like import OpenAILike
from paperless.config import AIConfig
from paperless.network import validate_outbound_http_url
@@ -22,8 +24,8 @@ class AIClient:
self.settings = AIConfig()
self.llm = self.get_llm()
def get_llm(self) -> "Ollama | OpenAI":
if self.settings.llm_backend == "ollama":
def get_llm(self) -> "Ollama | OpenAILike":
if self.settings.llm_backend == LLMBackend.OLLAMA:
from llama_index.llms.ollama import Ollama
endpoint = self.settings.llm_endpoint or "http://localhost:11434"
@@ -36,8 +38,8 @@ class AIClient:
base_url=endpoint,
request_timeout=120,
)
elif self.settings.llm_backend == "openai":
from llama_index.llms.openai import OpenAI
elif self.settings.llm_backend == LLMBackend.OPENAI_LIKE:
from llama_index.llms.openai_like import OpenAILike
endpoint = self.settings.llm_endpoint or None
if endpoint:
@@ -45,10 +47,12 @@ class AIClient:
endpoint,
allow_internal=self.settings.llm_allow_internal_endpoints,
)
return OpenAI(
return OpenAILike(
model=self.settings.llm_model or "gpt-3.5-turbo",
api_base=endpoint,
api_key=self.settings.llm_api_key,
is_chat_model=True,
is_function_calling_model=True,
)
else:
raise ValueError(f"Unsupported LLM backend: {self.settings.llm_backend}")

10
src/paperless_ai/embedding.py
View File

@@ -19,8 +19,8 @@ def get_embedding_model() -> "BaseEmbedding":
config = AIConfig()
match config.llm_embedding_backend:
case LLMEmbeddingBackend.OPENAI:
from llama_index.embeddings.openai import OpenAIEmbedding
case LLMEmbeddingBackend.OPENAI_LIKE:
from llama_index.embeddings.openai_like import OpenAILikeEmbedding
endpoint = config.llm_endpoint or None
if endpoint:
@@ -28,8 +28,8 @@ def get_embedding_model() -> "BaseEmbedding":
endpoint,
allow_internal=config.llm_allow_internal_endpoints,
)
return OpenAIEmbedding(
model=config.llm_embedding_model or "text-embedding-3-small",
return OpenAILikeEmbedding(
model_name=config.llm_embedding_model or "text-embedding-3-small",
api_key=config.llm_api_key,
api_base=endpoint,
)
@@ -54,7 +54,7 @@ def get_embedding_dim() -> int:
config = AIConfig()
model = config.llm_embedding_model or (
"text-embedding-3-small"
if config.llm_embedding_backend == "openai"
if config.llm_embedding_backend == LLMEmbeddingBackend.OPENAI_LIKE
else "sentence-transformers/all-MiniLM-L6-v2"
)

2
src/paperless_ai/tests/test_ai_indexing.py
View File

@@ -98,7 +98,7 @@ def test_update_llm_index_removes_meta(
config = AIConfig()
expected_model = config.llm_embedding_model or (
"text-embedding-3-small"
if config.llm_embedding_backend == "openai"
if config.llm_embedding_backend == "openai-like"
else "sentence-transformers/all-MiniLM-L6-v2"
)
assert meta == {"embedding_model": expected_model, "dim": 384}

10
src/paperless_ai/tests/test_client.py
View File

@@ -25,8 +25,8 @@ def mock_ollama_llm():
@pytest.fixture
def mock_openai_llm():
with patch("llama_index.llms.openai.OpenAI") as MockOpenAI:
yield MockOpenAI
with patch("llama_index.llms.openai_like.OpenAILike") as MockOpenAILike:
yield MockOpenAILike
def test_get_llm_ollama(mock_ai_config, mock_ollama_llm):
@@ -45,7 +45,7 @@ def test_get_llm_ollama(mock_ai_config, mock_ollama_llm):
def test_get_llm_openai(mock_ai_config, mock_openai_llm):
mock_ai_config.llm_backend = "openai"
mock_ai_config.llm_backend = "openai-like"
mock_ai_config.llm_model = "test_model"
mock_ai_config.llm_api_key = "test_api_key"
mock_ai_config.llm_endpoint = "http://test-url"
@@ -56,12 +56,14 @@ def test_get_llm_openai(mock_ai_config, mock_openai_llm):
model="test_model",
api_base="http://test-url",
api_key="test_api_key",
is_chat_model=True,
is_function_calling_model=True,
)
assert client.llm == mock_openai_llm.return_value
def test_get_llm_openai_blocks_internal_endpoint_when_disallowed(mock_ai_config):
mock_ai_config.llm_backend = "openai"
mock_ai_config.llm_backend = "openai-like"
mock_ai_config.llm_model = "test_model"
mock_ai_config.llm_api_key = "test_api_key"
mock_ai_config.llm_endpoint = "http://127.0.0.1:1234"

16
src/paperless_ai/tests/test_embedding.py
View File

@@ -54,15 +54,17 @@ def mock_document():
def test_get_embedding_model_openai(mock_ai_config):
mock_ai_config.return_value.llm_embedding_backend = LLMEmbeddingBackend.OPENAI
mock_ai_config.return_value.llm_embedding_backend = LLMEmbeddingBackend.OPENAI_LIKE
mock_ai_config.return_value.llm_embedding_model = "text-embedding-3-small"
mock_ai_config.return_value.llm_api_key = "test_api_key"
mock_ai_config.return_value.llm_endpoint = "http://test-url"
with patch("llama_index.embeddings.openai.OpenAIEmbedding") as MockOpenAIEmbedding:
with patch(
"llama_index.embeddings.openai_like.OpenAILikeEmbedding",
) as MockOpenAIEmbedding:
model = get_embedding_model()
MockOpenAIEmbedding.assert_called_once_with(
model="text-embedding-3-small",
model_name="text-embedding-3-small",
api_key="test_api_key",
api_base="http://test-url",
)
@@ -72,7 +74,7 @@ def test_get_embedding_model_openai(mock_ai_config):
def test_get_embedding_model_openai_blocks_internal_endpoint_when_disallowed(
mock_ai_config,
):
mock_ai_config.return_value.llm_embedding_backend = LLMEmbeddingBackend.OPENAI
mock_ai_config.return_value.llm_embedding_backend = LLMEmbeddingBackend.OPENAI_LIKE
mock_ai_config.return_value.llm_embedding_model = "text-embedding-3-small"
mock_ai_config.return_value.llm_api_key = "test_api_key"
mock_ai_config.return_value.llm_endpoint = "http://127.0.0.1:11434"
@@ -109,7 +111,7 @@ def test_get_embedding_model_invalid_backend(mock_ai_config):
def test_get_embedding_dim_infers_and_saves(temp_llm_index_dir, mock_ai_config):
mock_ai_config.return_value.llm_embedding_backend = "openai"
mock_ai_config.return_value.llm_embedding_backend = "openai-like"
mock_ai_config.return_value.llm_embedding_model = None
class DummyEmbedding:
@@ -129,7 +131,7 @@ def test_get_embedding_dim_infers_and_saves(temp_llm_index_dir, mock_ai_config):
def test_get_embedding_dim_reads_existing_meta(temp_llm_index_dir, mock_ai_config):
mock_ai_config.return_value.llm_embedding_backend = "openai"
mock_ai_config.return_value.llm_embedding_backend = "openai-like"
mock_ai_config.return_value.llm_embedding_model = None
(temp_llm_index_dir / "meta.json").write_text(
@@ -142,7 +144,7 @@ def test_get_embedding_dim_reads_existing_meta(temp_llm_index_dir, mock_ai_confi
def test_get_embedding_dim_raises_on_model_change(temp_llm_index_dir, mock_ai_config):
mock_ai_config.return_value.llm_embedding_backend = "openai"
mock_ai_config.return_value.llm_embedding_backend = "openai-like"
mock_ai_config.return_value.llm_embedding_model = None
(temp_llm_index_dir / "meta.json").write_text(

81
uv.lock generated
View File

@@ -2199,6 +2199,18 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/4e/d1/4bb0b80f4057903110060f617ef519197194b3ff5dd6153d850c8f5676fa/llama_index_embeddings_openai-0.6.0-py3-none-any.whl", hash = "sha256:039bb1007ad4267e25ddb89a206dfdab862bfb87d58da4271a3919e4f9df4d61", size = 7666, upload-time = "2026-03-12T20:21:28.079Z" },
]
[[package]]
name = "llama-index-embeddings-openai-like"
version = "0.3.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "llama-index-embeddings-openai", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
]
sdist = { url = "https://files.pythonhosted.org/packages/b2/df/79e4748196213b55931d5f8377141fff41135f5988d5501860824cc95390/llama_index_embeddings_openai_like-0.3.1.tar.gz", hash = "sha256:cef7af4bce284e8e6730532dbd0aa325e77398a5d5524edb2d2e3acb122fb5b6", size = 3854, upload-time = "2026-03-13T16:15:20.647Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/01/8e/b9ea889f88318f2faa20b615989e12a15a133c9273630f9266fcf69f35a6/llama_index_embeddings_openai_like-0.3.1-py3-none-any.whl", hash = "sha256:167c7e462cde7d53ea907ceaffbbf10a750676c7c9f7bcc9bc9686a41921387a", size = 3631, upload-time = "2026-03-13T16:15:19.58Z" },
]
[[package]]
name = "llama-index-instrumentation"
version = "0.4.2"
@@ -2238,6 +2250,19 @@ wheels = [
{ url = "https://files.pythonhosted.org/packages/63/62/a847e9a94c2f92926c30188259f9f86e019dcc45122bbb222dea35a74c02/llama_index_llms_openai-0.7.5-py3-none-any.whl", hash = "sha256:c302c6386873420df3714c3d538f45379b6de27ab6a531f30c67419b39a538f5", size = 28492, upload-time = "2026-03-30T16:30:32.979Z" },
]
[[package]]
name = "llama-index-llms-openai-like"
version = "0.7.2"
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/3b/a3/16410b28d131aa113ada79f856b78cb68a8e92a1e27255ea9c36c27a5dec/llama_index_llms_openai_like-0.7.2.tar.gz", hash = "sha256:ed9ff73f975dce470f98ac61c982151ba78eedfa3fb9b03894bc1d1312b213ff", size = 5389, upload-time = "2026-04-23T23:05:32.525Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/f4/0c/fdddaee5391d915d3d568d2d8dbdb7c95647e65bb94d4ddb31d47cef5daf/llama_index_llms_openai_like-0.7.2-py3-none-any.whl", hash = "sha256:1f45a7b1cec8fb3f5997684327ffe6c19f93e789c2fff35dc5522465850faf0b", size = 6602, upload-time = "2026-04-23T23:05:31.708Z" },
]
[[package]]
name = "llama-index-vector-stores-faiss"
version = "0.6.0"
@@ -2881,9 +2906,9 @@ dependencies = [
{ name = "langdetect", 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-embeddings-openai-like", 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-llms-openai-like", 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'" },
@@ -3030,9 +3055,9 @@ requires-dist = [
{ name = "langdetect", specifier = "~=1.0.9" },
{ name = "llama-index-core", specifier = ">=0.14.12" },
{ name = "llama-index-embeddings-huggingface", specifier = ">=0.6.1" },
{ name = "llama-index-embeddings-openai", specifier = ">=0.5.1" },
{ name = "llama-index-embeddings-openai-like", specifier = ">=0.2.2" },
{ name = "llama-index-llms-ollama", specifier = ">=0.9.1" },
{ name = "llama-index-llms-openai", specifier = ">=0.6.13" },
{ name = "llama-index-llms-openai-like", specifier = ">=0.7.1" },
{ name = "llama-index-vector-stores-faiss", specifier = ">=0.5.2" },
{ name = "mysqlclient", marker = "extra == 'mariadb'", specifier = "~=2.2.7" },
{ name = "nltk", specifier = "~=3.9.1" },
@@ -4919,12 +4944,12 @@ dependencies = [
{ name = "typing-extensions", marker = "sys_platform == 'darwin'" },
]
wheels = [
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d75eadcd97fe0dc7cd0eedc4d72152484c19cb2cfe46ce55766c8e129116425f" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:43b35116802c85fb88d99f4a396b8bd4472bfca1dd82e69499e5a4f9b8b4e252" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:442ec9dc78592564fdad69cf0beaa9da2f82ab810ccb4f13903869a90bf3f15d" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:cc3a195701bba2239c313ee311487f80f8aaebe9e89b9073dddbcf2f93b5a0ba" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:072a0d6e4865e8b0dc0dbfe6ebed68fae235124222835ef03e5814d414d8c012" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:23ec7789017da9d95b6d543d790814785e6f30905c5443efa8257d1490d73f79" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d75eadcd97fe0dc7cd0eedc4d72152484c19cb2cfe46ce55766c8e129116425f", upload-time = "2026-03-23T15:16:54Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:43b35116802c85fb88d99f4a396b8bd4472bfca1dd82e69499e5a4f9b8b4e252", upload-time = "2026-03-23T15:16:58Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:442ec9dc78592564fdad69cf0beaa9da2f82ab810ccb4f13903869a90bf3f15d", upload-time = "2026-03-23T15:17:02Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:cc3a195701bba2239c313ee311487f80f8aaebe9e89b9073dddbcf2f93b5a0ba", upload-time = "2026-03-23T15:17:06Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:072a0d6e4865e8b0dc0dbfe6ebed68fae235124222835ef03e5814d414d8c012", upload-time = "2026-03-23T15:17:10Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:23ec7789017da9d95b6d543d790814785e6f30905c5443efa8257d1490d73f79", upload-time = "2026-03-23T15:17:14Z" },
]
[[package]]
@@ -4947,24 +4972,24 @@ dependencies = [
{ name = "typing-extensions", marker = "sys_platform == 'linux'" },
]
wheels = [
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp311-cp311-linux_s390x.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp311-cp311-manylinux_2_28_aarch64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp311-cp311-manylinux_2_28_x86_64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp312-cp312-linux_s390x.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp312-cp312-manylinux_2_28_aarch64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp312-cp312-manylinux_2_28_x86_64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313-linux_s390x.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313-manylinux_2_28_aarch64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313-manylinux_2_28_x86_64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313t-linux_s390x.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313t-manylinux_2_28_aarch64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313t-manylinux_2_28_x86_64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314-linux_s390x.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314-manylinux_2_28_aarch64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314-manylinux_2_28_x86_64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314t-linux_s390x.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314t-manylinux_2_28_aarch64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314t-manylinux_2_28_x86_64.whl" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp311-cp311-linux_s390x.whl", hash = "sha256:5214b203ee187f8746c66f1378b72611b7c1e15c5cb325037541899e705ea24e", upload-time = "2026-04-27T21:55:40Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:46fbb0aa257bb781efbfad648f5b045c0e232573b661f1461593db61342e9096", upload-time = "2026-04-28T00:05:38Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:8a56a8c95531ef0e454510ba8bbd9d11dc7a9000337265210b10f6bfeacdd485", upload-time = "2026-04-28T00:05:47Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp312-cp312-linux_s390x.whl", hash = "sha256:2db3ae5404e32cb42b5fcbd94f13607761eaec0cf1687fde95095289d1e26cfb", upload-time = "2026-04-28T00:06:06Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:70ecb2659af6373b7c5336e692e665605b0201ea21ff51aaea47e1d75ea6b5aa", upload-time = "2026-04-28T00:06:14Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:f82e2ae20c1545bb03997d1cc3143d94e14b800038669ee1aca45808a9acc338", upload-time = "2026-04-28T00:06:24Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313-linux_s390x.whl", hash = "sha256:d1eff25ccc454faf21c9666c81bfab8e405e87c12d300708d4559620bc191a36", upload-time = "2026-04-28T00:06:42Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:48b3e21a311445acdd0b27f13830e21d93adef70d4721e051e9f059baeb9b8f9", upload-time = "2026-04-28T00:06:51Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:45025d7752dbc6b4c784c03afaee9c5f19730ce084b2e43fc9a2fe1677d9ff86", upload-time = "2026-04-28T00:07:02Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313t-linux_s390x.whl", hash = "sha256:65d427a196ab0abe359b93c5bffedd76ded02df2b1b1d2d9f11a2609b69f426a", upload-time = "2026-04-28T00:07:19Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:8f13dc7075ae04ca5f876a9f40b4e47522a04c23e30824b4409f42a3f3e57aa4", upload-time = "2026-04-28T00:07:27Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:8713bb8679376ea0ec25742100b6cfb8447e0904c48bddefb9eb0ac1abbfa60a", upload-time = "2026-04-28T00:07:37Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314-linux_s390x.whl", hash = "sha256:c9a14c367f470623b978e273a4e1915995b4ba7a0ae999178b06c273eea3536f", upload-time = "2026-04-28T00:07:54Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:71676f6a9a84bbd385e010198b51fa1c2324fb8f3c512a32d2c81af65f68f4c9", upload-time = "2026-04-28T00:08:02Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314-manylinux_2_28_x86_64.whl", hash = "sha256:f8481ea9088e4e5b81178a75aabdbb658bde8639bc1a15fd5d8f930abc966735", upload-time = "2026-04-28T00:08:11Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314t-linux_s390x.whl", hash = "sha256:825f1596878280a3a4c861441674888bc2d792e4ab7b045cb35feeab3f4f5dd7", upload-time = "2026-04-28T00:08:27Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:c8a0bdfb2fd915b6c2cd27c856f63f729c366a4917772eba6b2b02aa3bce70d5", upload-time = "2026-04-28T00:08:36Z" },
{ url = "https://download-r2.pytorch.org/whl/cpu/torch-2.11.0%2Bcpu-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:768f22924a25cad2adeb9c6cbac5159e71067c8d4019b1511960d7435a5ca652", upload-time = "2026-04-28T00:08:47Z" },
]
[[package]]