retab 0.0.41__py3-none-any.whl → 0.0.42__py3-none-any.whl

retab/types/documents/parse.py

@@ -3,6 +3,7 @@ from pydantic import BaseModel, Field
 
 from ..mime import MIMEData, BaseMIMEData
 from ..browser_canvas import BrowserCanvas
+from ..ai_models import LLMModel
 
 TableParsingFormat = Literal["markdown", "yaml", "html", "json"]
 
@@ -18,7 +19,7 @@ class ParseRequest(BaseModel):
     """Request model for document parsing."""
 
     document: MIMEData = Field(..., description="Document to parse")
-    fast_mode: bool = Field(default=False, description="Use fast mode for parsing (may reduce quality)")
+    model: LLMModel = Field(default="gemini-2.5-flash", description="Model to use for parsing")
     table_parsing_format: TableParsingFormat = Field(default="html", description="Format for parsing tables")
     image_resolution_dpi: int = Field(default=72, description="DPI for image processing")
     browser_canvas: BrowserCanvas = Field(default="A4", description="Canvas size for document rendering")
@@ -30,3 +31,4 @@ class ParseResult(BaseModel):
     document: BaseMIMEData = Field(..., description="Processed document metadata")
     usage: RetabUsage = Field(..., description="Processing usage information")
     pages: list[str] = Field(..., description="Text content of each page")
+    text: str = Field(..., description="Text content of the document")

retab/types/extractions.py

@@ -3,13 +3,19 @@ from typing import Any, Literal, Optional
 
 import nanoid  # type: ignore
 from openai.types.chat import ChatCompletion
-from openai.types.chat.chat_completion_reasoning_effort import ChatCompletionReasoningEffort
+from openai.types.chat.chat_completion_reasoning_effort import (
+    ChatCompletionReasoningEffort,
+)
 from pydantic import BaseModel, Field, computed_field, model_validator
 
 from retab.types.chat import ChatCompletionRetabMessage
 from retab.types.documents.extractions import RetabParsedChatCompletion
 
-from ..utils.usage.usage import CostBreakdown, compute_cost_from_model, compute_cost_from_model_with_breakdown
+from ..utils.usage.usage import (
+    CostBreakdown,
+    compute_cost_from_model,
+    compute_cost_from_model_with_breakdown,
+)
 from .ai_models import Amount
 from .modalities import Modality
 
@@ -17,9 +23,18 @@ ValidationsState = Literal["pending", "validated", "invalid"]
 
 
 class ExtractionSource(BaseModel):
-    type: Literal["api", "annotation", "processor", "automation.link", "automation.mailbox", "automation.cron", "automation.outlook", "automation.endpoint", "schema.extract"] = (
-        Field(description="Type of extraction")
-    )
+    type: Literal[
+        "api",
+        "annotation",
+        "processor",
+        "automation",
+        "automation.link",
+        "automation.mailbox",
+        "automation.cron",
+        "automation.outlook",
+        "automation.endpoint",
+        "schema.extract",
+    ] = Field(description="Type of extraction")
     id: str | None = Field(default=None, description="ID the trigger of the extraction")
 
 
@@ -34,7 +49,10 @@ class ExtractionTimingStep(BaseModel):
 
 
 class Extraction(BaseModel):
-    id: str = Field(default_factory=lambda: "extr_" + nanoid.generate(), description="Unique identifier of the analysis")
+    id: str = Field(
+        default_factory=lambda: "extr_" + nanoid.generate(),
+        description="Unique identifier of the analysis",
+    )
     messages: list[ChatCompletionRetabMessage] = Field(default_factory=list)
     messages_gcs: str = Field(..., description="GCS path to the messages")
     file_gcs_paths: list[str] = Field(..., description="GCS paths to the files")
@@ -51,16 +69,23 @@ class Extraction(BaseModel):
     source: ExtractionSource = Field(..., description="Source of the extraction")
     image_resolution_dpi: int = Field(default=96, description="Resolution of the image sent to the LLM")
     browser_canvas: BrowserCanvas = Field(
-        default="A4", description="Sets the size of the browser canvas for rendering documents in browser-based processing. Choose a size that matches the document type."
+        default="A4",
+        description="Sets the size of the browser canvas for rendering documents in browser-based processing. Choose a size that matches the document type.",
     )
     modality: Modality = Field(default="native", description="Modality of the extraction")
-    reasoning_effort: Optional[ChatCompletionReasoningEffort] = Field(default=None, description="The effort level for the model to reason about the input data.")
+    reasoning_effort: Optional[ChatCompletionReasoningEffort] = Field(
+        default=None,
+        description="The effort level for the model to reason about the input data.",
+    )
     timings: list[ExtractionTimingStep] = Field(default_factory=list, description="Timings of the extraction")
 
     # Infered from the schema
     schema_id: str = Field(..., description="Version of the schema used for the analysis")
     schema_data_id: str = Field(..., description="Version of the schema data used for the analysis")
-    created_at: datetime.datetime = Field(default_factory=lambda: datetime.datetime.now(datetime.timezone.utc), description="Timestamp of the creation of the extraction object")
+    created_at: datetime.datetime = Field(
+        default_factory=lambda: datetime.datetime.now(datetime.timezone.utc),
+        description="Timestamp of the creation of the extraction object",
+    )
     request_at: datetime.datetime | None = Field(default=None, description="Timestamp of the extraction request if provided.")
     organization_id: str = Field(..., description="Organization ID of the user or application")
     validation_state: Optional[ValidationsState] = Field(default=None, description="Validation state of the extraction")

retab-0.0.42.dist-info/METADATA

@@ -0,0 +1,119 @@
+Metadata-Version: 2.1
+Name: retab
+Version: 0.0.42
+Summary: Retab official python library
+Home-page: https://github.com/Retab-dev/retab
+Author: Retab
+Author-email: contact@retab.com
+Project-URL: Team website, https://retab.com
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: MacOS
+Classifier: Intended Audience :: Science/Research
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Requires-Dist: Pillow
+Requires-Dist: httpx
+Requires-Dist: pydantic
+Requires-Dist: pydantic-core
+Requires-Dist: requests
+Requires-Dist: tqdm
+Requires-Dist: types-tqdm
+Requires-Dist: backoff
+Requires-Dist: termplotlib
+Requires-Dist: Levenshtein
+Requires-Dist: pandas
+Requires-Dist: numpy
+Requires-Dist: motor
+Requires-Dist: rich
+Requires-Dist: puremagic
+Requires-Dist: pycountry
+Requires-Dist: phonenumbers
+Requires-Dist: email-validator
+Requires-Dist: python-stdnum
+Requires-Dist: nanoid
+Requires-Dist: openai
+Requires-Dist: google-genai
+Requires-Dist: google-generativeai
+Requires-Dist: anthropic
+Requires-Dist: tiktoken
+Requires-Dist: truststore
+Requires-Dist: ruff
+
+# Retab
+
+<div align="center" style="margin-bottom: 1em;">
+
+<img src="https://raw.githubusercontent.com/Retab-dev/retab/refs/heads/main/assets/retab-logo.png" alt="Retab Logo" width="150">
+
+
+  *The AI Automation Platform*
+
+Made with love by the team at [Retab](https://retab.com) 🤍.
+
+[Our Website](https://retab.com) | [Documentation](https://docs.retab.com/get-started/introduction) | [Discord](https://discord.com/invite/vc5tWRPqag) | [Twitter](https://x.com/retabdev)
+
+
+</div>
+
+---
+
+### What is Retab?
+
+Retab solves all the major challenges in document processing with LLMs:
+
+1. **Universal Document Preprocessing**: Convert any file type (PDFs, Excel, emails, etc.) into LLM-ready format without writing custom parsers
+2. **Structured, Schema-driven Extraction**: Get consistent, reliable outputs using schema-based prompt engineering
+3. **Processors**: Publish a live, stable, shareable document processor.
+4. **Automations**: Create document processing workflows that can be triggered by events (mailbox, upload link, endpoint, outlook plugin).
+5. **Evaluations**: Evaluate the performance of models against annotated datasets
+6. **Optimizations**: Identify the most used processors and help you finetune models to reduce costs and improve performance
+
+We are offering you all the software-defined primitives to build your own document processing solutions. We see it as **Stripe** for document processing.
+
+Our goal is to make the process of analyzing documents and unstructured data as **easy** and **transparent** as possible.
+
+**A new, lighter paradigm**
+Large Language Models collapse entire layers of legacy OCR pipelines into a single, elegant abstraction. When a model can read, reason, and structure text natively, we no longer need brittle heuristics, handcrafted parsers, or heavyweight ETL jobs. Instead, we can expose a small, principled API: "give me the document, tell me the schema, and get back structured truth." Complexity evaporates, reliability rises, speed follows, and costs fall—because every component you remove is one that can no longer break. LLM‑first design lets us focus less on plumbing and more on the questions we actually want answered.
+
+Many people haven't yet realized how powerful LLMs have become at document processing tasks - we're here to help **unlock these capabilities**.
+
+---
+
+## Go further
+
+* [Quickstart](/get-started/quickstart)
+* [API Reference](/api-reference/introduction)
+
+---
+
+## Code examples
+
+## You can check our Github repository to see code examples: [python examples](https://github.com/Retab-dev/retab/tree/main/examples) and [jupyter notebooks](https://github.com/Retab-dev/retab-nodejs/tree/main/notebooks).
+
+## Community
+
+Let's create the future of document processing together!
+
+Join our [discord community](https://discord.com/invite/vc5tWRPqag) to share tips, discuss best practices, and showcase what you build. Or just [tweet](https://x.com/retabdev) at us.
+
+We can't wait to see how you'll use Retab.
+
+* [Discord](https://discord.com/invite/vc5tWRPqag)
+* [Twitter](https://x.com/retabdev)
+
+---
+
+## Roadmap
+
+We share our roadmap publicly on [Github](https://github.com/Retab-dev/retab)
+
+Among the features we're working on:
+
+* [ ] Node.js SDK
+* [ ] Low-level speed optimizations for Evals Frontend
+* [ ] Schema optimization autopilot
+* [ ] Sources API
+* [ ] Parse API for RAG
+

{retab-0.0.41.dist-info → retab-0.0.42.dist-info}/RECORD

@@ -1,6 +1,6 @@
 retab/__init__.py,sha256=sRurau6z8m4pn7VFKdHr9FyNA9Ffhvg064i2NF0RmPc,124
 retab/_resource.py,sha256=JfAU4UTa05ugWfbrpO7fsVr_pFewht99NkoIfK6kBQM,577
-retab/client.py,sha256=ebU_g0BfIJ6Lz-XsHjlMtomTBy4V_lDDgLTC0AYzDZE,29768
+retab/client.py,sha256=gbBSkOWbXLoYXwRGXkhubBeIxAecVHvW_3b9ELNSE2Q,29768
 retab/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 retab/_utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 retab/_utils/ai_models.py,sha256=u0SDwSd3SNhJaFm6bPepiGIh4BbocGYDKk4qu3kVIxc,4821
@@ -31,26 +31,26 @@ retab/resources/usage.py,sha256=OmJMPwmP1TBuZmMKrjaGWnl2mQ9VbQDKSAm6l7Tsaf4,1360
 retab/resources/consensus/__init__.py,sha256=0b3MSOFiYPwkNTrs_dBPRhwSl3kuk8BtG5QXofIUb9M,89
 retab/resources/consensus/client.py,sha256=D2TeqqCp0ZvqvQLAe1i3nW8nnf-Ms6zNEXRA9C26TQI,3705
 retab/resources/consensus/completions.py,sha256=6vTnqADY6GueV28smYRDQ2yooj94G2WHMlQLyKOXqtw,8372
-retab/resources/consensus/completions_stream.py,sha256=JQdOsWunY60nNSsrz3V4SA6OUXx_IxRsKjg1fjq2QSs,10893
+retab/resources/consensus/completions_stream.py,sha256=DlU9od01F1Fmh9WjTLhq4KsntfqXy5jGGwrYauS43Ec,10893
 retab/resources/consensus/responses.py,sha256=av__D_3hs8GlV7RnBnrLmtjq6_DzbWwfSP8lzjiHlw8,9935
 retab/resources/consensus/responses_stream.py,sha256=OopJ9aoO7HctfhLnXzJx8-dkk-4jK_juOw6jUAkzwVM,11671
 retab/resources/documents/__init__.py,sha256=OjXmngFN0RKqO4SI-mJBNzr6Ex6rMxfq0DxaqzP0RQs,89
-retab/resources/documents/client.py,sha256=K1G63fRdd5T-HjmYsoW-6V7hXT8o9L2F15qIGBfWC5c,25361
+retab/resources/documents/client.py,sha256=fTaNecDke_fGEcqQIcTJcGZDKhSMWgZl2bxc6W48oOg,25295
 retab/resources/documents/extractions.py,sha256=jMBgirKohgMTsdwX-LQldmvgHVHt-Q2N5810K1tzk9Q,25623
 retab/resources/evaluations/__init__.py,sha256=3npbUDbxYn3ihnUKV7PRYNBYqL7MZ9AwhQHr7LaIESg,97
 retab/resources/evaluations/client.py,sha256=SdI-m_8V0BApparlHO1mYFwvjAGWsHBKD_-Z3ZLcdq0,10658
 retab/resources/evaluations/documents.py,sha256=G58AYRpmlGRspwuunwhWB_cqN_Zn5Ukp_f2NAMyxMi4,9489
 retab/resources/evaluations/iterations.py,sha256=v9kD1tJ-3I0A02zVIwSInKHwPzGhmub7fc5FEBJkT74,17664
 retab/resources/processors/__init__.py,sha256=w1HrMdSi3xlrcEDFMQ9BA7rbUhOFWSTkTKkkR2PfFHQ,93
-retab/resources/processors/client.py,sha256=s5OddrzUF-kue8-58jbwOfN4a5yk3dgtpMCnlpPjlPU,20710
+retab/resources/processors/client.py,sha256=EMu7VlniDePhPvlCryGwXWaG2wketLA6vz8JUFs8U0A,20710
 retab/resources/processors/automations/__init__.py,sha256=Iej-_yIxc8xAuhYmR0e2VI7j_EXVsNk1_L98OJSD82E,121
 retab/resources/processors/automations/client.py,sha256=3w54F0JfC2GYDosLux8LVEjDd_RXqQ29-SyNXGa28U8,10500
-retab/resources/processors/automations/endpoints.py,sha256=EulA5993Kj42uAhcWbnZdYwF5ppColOlOIW0Pz1Ujnc,10895
-retab/resources/processors/automations/links.py,sha256=HBfpouFBxwjIyDWHyG15XwYRC2lLJLkcywmTUnjQcPI,11449
-retab/resources/processors/automations/logs.py,sha256=Ft0cH6C2zbm4dLdiQ-3hqC8HU8-23bGOjUGbaauDNAU,8827
-retab/resources/processors/automations/mailboxes.py,sha256=PAZzkchZdekyesJxo42GGjrCvimUvGfv8E3dBYvjql8,15907
-retab/resources/processors/automations/outlook.py,sha256=Zj_sVxpDLCNxh1xaTAZ6GMGd26KtFo7QXrmalUpi4xA,14919
-retab/resources/processors/automations/tests.py,sha256=9LDZltHgHOOoJT1apkvB_aaM96WlzCDPtsoyMN3UWrA,5991
+retab/resources/processors/automations/endpoints.py,sha256=9ur3OR1b-gKaM4JqiQVaWUS0DmkfNvYgbi_TkbyoXQ4,11046
+retab/resources/processors/automations/links.py,sha256=LXOnDlaei07MRIc5KfxhCS5QikE8g0uptuYFeimXFPg,11449
+retab/resources/processors/automations/logs.py,sha256=seBjzv4Tm8fMJcApzZcyR5yXG5YLP0yW5BH5ql7JMcg,8827
+retab/resources/processors/automations/mailboxes.py,sha256=7TQcUDM9iX_E_Yg_r2l59Jxf-1p30bx4jTMY-rgD5MQ,16155
+retab/resources/processors/automations/outlook.py,sha256=ANX0MftT4VQt8ehZkhN1xpaccph9pDNXYLbO2WW3wsw,15189
+retab/resources/processors/automations/tests.py,sha256=nbO6qIkQnpr629ZkCchbfCJOm7KyjDOaLsxXxB3i0cg,6219
 retab/resources/secrets/__init__.py,sha256=SwofMyk96k0YSyj1d_GRxhpVx4wb4TA97TISsTjB0Kc,105
 retab/resources/secrets/client.py,sha256=nXt1cgvkWqhA99WTnC1PWbWJq-EbwvoDuCQOa0GJOOU,599
 retab/resources/secrets/external_api_keys.py,sha256=3TuJxjk65EPUT2XC3wBcYWaVwqzc6QGv9BoHufzxTLU,3759
@@ -63,7 +63,7 @@ retab/types/completions.py,sha256=ZQU29bm-FhdOzky4_Dp2N--fedR82C3QfCRZCJCQ-P8,53
 retab/types/consensus.py,sha256=EsFCsyZK8NhkQ1BizFpnGN54D24hRFKc0xwt9VpH11c,1161
 retab/types/evals.py,sha256=JNdWu4hplfSEuSzu9l27ZVr2RO2opUKEruIpKXZosmU,9953
 retab/types/events.py,sha256=NrisdzJAaJ_kkfgdsqoiDB-Upm0LnbIGZikU_e9XXWw,2195
-retab/types/extractions.py,sha256=3l-RW9iUUVHqWBnbfoUO7I3VREAJdDqHUQaNAJ0NKR8,5849
+retab/types/extractions.py,sha256=Pvzu2Bu62X6P055xDj6Du8kf_ilJBiyeYl_uN5GfGVw,6038
 retab/types/inference_settings.py,sha256=F_mBPFVY1yAwsHD11Z2ljMf3zkvviOey_JBnu8yEF84,572
 retab/types/logs.py,sha256=uWgul1YpbczzWozuVnBWuVMm6NAZElSE1rXs_O8A98s,9260
 retab/types/metrics.py,sha256=0KEWUWW13s_tWjh7oUs33ip9TPwI7LZUNGE7k5qNoOo,1947
@@ -76,7 +76,7 @@ retab/types/automations/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG
 retab/types/automations/cron.py,sha256=jDx0VzciboQw2_whvBXzgX5ZS0z2DksTgmyhXCSSGMk,3174
 retab/types/automations/endpoints.py,sha256=IbylkBUBllcrtr9tifug0ptVq2vFKixuQ6e2JfW5Xfw,666
 retab/types/automations/links.py,sha256=1ipBFWasY3cqds0U5AUz9Ez6T5kcgzX5r0gzZvFw8tU,901
-retab/types/automations/mailboxes.py,sha256=KZh2BiQ8Q-HgNQT672Sl97LDnqW2sgjY_W3ZEj7o4Ow,2332
+retab/types/automations/mailboxes.py,sha256=3LDmEZO1RtsNq-5Q7jVjfTo7o92rYK-UH56Ja-dKJ9Q,2332
 retab/types/automations/outlook.py,sha256=4rJ-_1Py88n44ASdWJHpb0_V5VKafP7pj67ovi6iYwU,3040
 retab/types/automations/webhooks.py,sha256=_IY33_RL8ULYmKW7vYbCXLCEmsrKzM9SmwdPyv6LfwM,571
 retab/types/db/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -85,8 +85,8 @@ retab/types/db/files.py,sha256=udJKGplw6a8cF4XUTLN_QAU9-pyEWs4THHX1zyvbx0U,1261
 retab/types/documents/__init__.py,sha256=RaD6PnvRJw7QEVTh_PYNX6gckpLcxUJH7FKaopRKJzY,114
 retab/types/documents/correct_orientation.py,sha256=e-ivsslI6L6Gl0YkcslXw_DH620xMGEYVp4tdeviXeM,261
 retab/types/documents/create_messages.py,sha256=S2nJ4GHZ3hKTZ4kNs5XrCZeaokOsy9LqRC-FVHkFvSY,10285
-retab/types/documents/extractions.py,sha256=TyxUmkDbP-OB2LlC6gB5PkJ_z5cyq7atsS2EWKlJ8z0,19112
-retab/types/documents/parse.py,sha256=WCfwBUsMgYFAZWbuOgCPd2dkcFmi1fYOf21XuiIj4uo,1323
+retab/types/documents/extractions.py,sha256=z1XlQLeCGcUAipVB8WGbbUjaBor1bN9BxQzeBaDMj3E,19096
+retab/types/documents/parse.py,sha256=-gCzloJhZraR_Pi9Je0SL8aP52n0GfO9qH838usPA3w,1418
 retab/types/evaluations/__init__.py,sha256=fRQlK6y3x3SHqaukVYd9_zH8HrUk9TpoG9dlOTuIkcY,920
 retab/types/evaluations/documents.py,sha256=oy0nqTrv0Pe__5ligeNWn5MbqVDAFRSrXYbCVoLxyXw,1268
 retab/types/evaluations/iterations.py,sha256=lVHcqmIT0AtJyn7dc_Mw-WbeA0gfTUG1KoifCOFPIkg,4635
@@ -123,7 +123,7 @@ retab/utils/_model_cards/openai.yaml,sha256=PcmjqAioomqWOw25H4BluVfJ1WO_zapg_nPx
 retab/utils/_model_cards/xai.yaml,sha256=OdVV33_WODc4UBZhDezcUq_5mHQK5zeOT49EjJUJ764,612
 retab/utils/usage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 retab/utils/usage/usage.py,sha256=PoQAMSWqEXYIRdp-JW9HjecFVitD_oMbxDMtDJdqWnQ,12948
-retab-0.0.41.dist-info/METADATA,sha256=XhOqB_OlYbAsLh0tB4ce8gKqBrQnM-7QG9oTFCMPcNs,14142
-retab-0.0.41.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
-retab-0.0.41.dist-info/top_level.txt,sha256=waQR0EGdhLIQtztoE3AXg7ik5ONQ9q_bsKVpyFuJdq0,6
-retab-0.0.41.dist-info/RECORD,,
+retab-0.0.42.dist-info/METADATA,sha256=iXf44YON_rAIYSUqLblaiAahfFIMoyTivm1UkPYxrx8,4549
+retab-0.0.42.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+retab-0.0.42.dist-info/top_level.txt,sha256=waQR0EGdhLIQtztoE3AXg7ik5ONQ9q_bsKVpyFuJdq0,6
+retab-0.0.42.dist-info/RECORD,,