langcore-rag 1.0.0__tar.gz

langcore_rag-1.0.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 Gabriel Ignat
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

langcore_rag-1.0.0/PKG-INFO

@@ -0,0 +1,191 @@
+Metadata-Version: 2.4
+Name: langcore-rag
+Version: 1.0.0
+Summary: RAG query parsing plugin — parse natural language queries into semantic terms and structured filters using LLMs
+License-Expression: Apache-2.0
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: langextract-core>=1.1.0
+Requires-Dist: litellm>=1.81.13
+Requires-Dist: pydantic>=2.12.0
+Dynamic: license-file
+
+# LangCore RAG — Query Parsing for Hybrid Retrieval
+
+A plugin for [LangExtract](https://github.com/google/langextract) that parses natural-language queries into **semantic terms** (for vector search) and **structured metadata filters** (for database / index filtering), enabling hybrid RAG retrieval pipelines. Inspired by [LangStruct](https://github.com/langstruct/langstruct)'s `.query()` method.
+
+> **Note**: This is a third-party plugin for LangExtract. For the main LangExtract library, visit [google/langextract](https://github.com/google/langextract).
+
+## Installation
+
+Install from source:
+
+```bash
+git clone <repo-url>
+cd langcore-rag
+pip install -e .
+```
+
+Or with [uv](https://docs.astral.sh/uv/):
+
+```bash
+uv pip install -e .
+```
+
+## Features at a Glance
+
+| Feature | langcore-rag | LangStruct |
+|---|---|---|
+| **Query → semantic terms + filters** | ✅ `QueryParser.parse()` | ✅ `.query()` |
+| **Async support** | ✅ `async_parse()` | ✅ |
+| **Pydantic schema introspection** | ✅ Auto-discovers filterable fields | ✅ |
+| **MongoDB-style operators** | ✅ `$eq`, `$gte`, `$lte`, `$in`, `$nin`, etc. | ✅ |
+| **Confidence score** | ✅ 0.0 – 1.0 | ❌ |
+| **Explanation / rationale** | ✅ Human-readable | ❌ |
+| **Any LLM backend** | ✅ Via LiteLLM (100+ providers) | ✅ |
+| **Robust JSON parsing** | ✅ Raw JSON + Markdown fences + graceful fallback | ⚠️ |
+
+## Quick Start
+
+### 1. Define a Schema
+
+```python
+from pydantic import BaseModel, Field
+
+class Invoice(BaseModel):
+    amount: float = Field(description="Total invoice amount in USD")
+    due_date: str = Field(description="Due date in ISO-8601 format")
+    vendor: str = Field(description="Vendor / supplier name")
+    paid: bool = Field(description="Whether the invoice is paid")
+```
+
+### 2. Parse a Query
+
+```python
+from langcore_rag import QueryParser
+
+parser = QueryParser(schema=Invoice, model_id="gemini/gemini-2.5-flash")
+parsed = parser.parse("invoices over $5000 due in March 2024")
+
+print(parsed.semantic_terms)
+# → ["invoices"]
+
+print(parsed.structured_filters)
+# → {"amount": {"$gte": 5000}, "due_date": {"$gte": "2024-03-01", "$lte": "2024-03-31"}}
+
+print(parsed.confidence)
+# → 0.92
+
+print(parsed.explanation)
+# → "Extracted amount ≥ 5000 and date range for March 2024."
+```
+
+### 3. Async Usage
+
+```python
+import asyncio
+from langcore_rag import QueryParser
+
+async def main():
+    parser = QueryParser(schema=Invoice, model_id="gpt-4o")
+    parsed = await parser.async_parse("unpaid invoices from Acme Corp")
+    print(parsed.structured_filters)
+    # → {"paid": {"$eq": false}, "vendor": {"$eq": "Acme Corp"}}
+
+asyncio.run(main())
+```
+
+## API Reference
+
+### `QueryParser`
+
+```python
+QueryParser(
+    schema: type[BaseModel],
+    model_id: str,
+    *,
+    temperature: float = 0.0,
+    max_tokens: int = 1024,
+    **litellm_kwargs,
+)
+```
+
+| Parameter | Type | Description |
+|---|---|---|
+| `schema` | `type[BaseModel]` | Pydantic model whose fields define filterable metadata |
+| `model_id` | `str` | Any LiteLLM-compatible model ID (e.g. `"gpt-4o"`, `"gemini/gemini-2.5-flash"`, `"anthropic/claude-3-opus"`) |
+| `temperature` | `float` | Sampling temperature (default `0.0` for deterministic output) |
+| `max_tokens` | `int` | Maximum tokens to generate (default `1024`) |
+| `**litellm_kwargs` | | Extra kwargs forwarded to `litellm.completion()` (e.g. `api_key`, `api_base`, `timeout`) |
+
+#### Methods
+
+| Method | Signature | Description |
+|---|---|---|
+| `parse` | `(query_text: str) -> ParsedQuery` | Synchronous query parsing |
+| `async_parse` | `(query_text: str) -> ParsedQuery` | Asynchronous query parsing |
+
+#### Properties
+
+| Property | Type | Description |
+|---|---|---|
+| `schema` | `type[BaseModel]` | The Pydantic schema used for field discovery |
+| `model_id` | `str` | The LiteLLM model identifier |
+| `system_prompt` | `str` | The generated system prompt (useful for debugging) |
+
+### `ParsedQuery`
+
+An immutable (frozen) dataclass returned by `parse()` / `async_parse()`.
+
+| Field | Type | Description |
+|---|---|---|
+| `semantic_terms` | `list[str]` | Free-text terms for vector / similarity search |
+| `structured_filters` | `dict[str, Any]` | Metadata filters with MongoDB-style operators |
+| `confidence` | `float` | 0.0 – 1.0 confidence in the parse quality |
+| `explanation` | `str` | Human-readable rationale for the decomposition |
+
+## How It Works
+
+1. **Schema introspection** — `QueryParser` inspects the Pydantic model's fields to identify which ones are scalar/filterable (`int`, `float`, `str`, `bool`, `date`, `datetime`). Complex types like `list[str]` are excluded.
+
+2. **System prompt generation** — A system prompt is built listing the filterable fields with their types and descriptions, instructing the LLM to output a JSON object with `semantic_terms`, `structured_filters`, `confidence`, and `explanation`.
+
+3. **LLM call** — The query text is sent as a user message alongside the system prompt via `litellm.completion()` (sync) or `litellm.acompletion()` (async).
+
+4. **Response parsing** — The LLM's text response is parsed as JSON (handling both raw JSON and Markdown code fences). Values are type-coerced and clamped to produce a valid `ParsedQuery`.
+
+## Supported Filter Operators
+
+The parser instructs the LLM to use MongoDB-style operators:
+
+| Operator | Meaning | Example |
+|---|---|---|
+| `$eq` | Equals | `{"vendor": {"$eq": "Acme"}}` |
+| `$ne` | Not equals | `{"paid": {"$ne": true}}` |
+| `$gt` | Greater than | `{"amount": {"$gt": 1000}}` |
+| `$gte` | Greater than or equal | `{"amount": {"$gte": 5000}}` |
+| `$lt` | Less than | `{"amount": {"$lt": 100}}` |
+| `$lte` | Less than or equal | `{"due_date": {"$lte": "2024-12-31"}}` |
+| `$in` | In list | `{"vendor": {"$in": ["Acme", "Globex"]}}` |
+| `$nin` | Not in list | `{"vendor": {"$nin": ["Initech"]}}` |
+
+## Development
+
+```bash
+# Install dev dependencies
+uv sync
+
+# Run tests
+uv run pytest tests/ -v
+
+# Lint
+uv run ruff check langcore_rag/ tests/
+
+# Format
+uv run ruff format langcore_rag/ tests/
+```
+
+## License
+
+[Apache 2.0](LICENSE)

langcore_rag-1.0.0/README.md

@@ -0,0 +1,178 @@
+# LangCore RAG — Query Parsing for Hybrid Retrieval
+
+A plugin for [LangExtract](https://github.com/google/langextract) that parses natural-language queries into **semantic terms** (for vector search) and **structured metadata filters** (for database / index filtering), enabling hybrid RAG retrieval pipelines. Inspired by [LangStruct](https://github.com/langstruct/langstruct)'s `.query()` method.
+
+> **Note**: This is a third-party plugin for LangExtract. For the main LangExtract library, visit [google/langextract](https://github.com/google/langextract).
+
+## Installation
+
+Install from source:
+
+```bash
+git clone <repo-url>
+cd langcore-rag
+pip install -e .
+```
+
+Or with [uv](https://docs.astral.sh/uv/):
+
+```bash
+uv pip install -e .
+```
+
+## Features at a Glance
+
+| Feature | langcore-rag | LangStruct |
+|---|---|---|
+| **Query → semantic terms + filters** | ✅ `QueryParser.parse()` | ✅ `.query()` |
+| **Async support** | ✅ `async_parse()` | ✅ |
+| **Pydantic schema introspection** | ✅ Auto-discovers filterable fields | ✅ |
+| **MongoDB-style operators** | ✅ `$eq`, `$gte`, `$lte`, `$in`, `$nin`, etc. | ✅ |
+| **Confidence score** | ✅ 0.0 – 1.0 | ❌ |
+| **Explanation / rationale** | ✅ Human-readable | ❌ |
+| **Any LLM backend** | ✅ Via LiteLLM (100+ providers) | ✅ |
+| **Robust JSON parsing** | ✅ Raw JSON + Markdown fences + graceful fallback | ⚠️ |
+
+## Quick Start
+
+### 1. Define a Schema
+
+```python
+from pydantic import BaseModel, Field
+
+class Invoice(BaseModel):
+    amount: float = Field(description="Total invoice amount in USD")
+    due_date: str = Field(description="Due date in ISO-8601 format")
+    vendor: str = Field(description="Vendor / supplier name")
+    paid: bool = Field(description="Whether the invoice is paid")
+```
+
+### 2. Parse a Query
+
+```python
+from langcore_rag import QueryParser
+
+parser = QueryParser(schema=Invoice, model_id="gemini/gemini-2.5-flash")
+parsed = parser.parse("invoices over $5000 due in March 2024")
+
+print(parsed.semantic_terms)
+# → ["invoices"]
+
+print(parsed.structured_filters)
+# → {"amount": {"$gte": 5000}, "due_date": {"$gte": "2024-03-01", "$lte": "2024-03-31"}}
+
+print(parsed.confidence)
+# → 0.92
+
+print(parsed.explanation)
+# → "Extracted amount ≥ 5000 and date range for March 2024."
+```
+
+### 3. Async Usage
+
+```python
+import asyncio
+from langcore_rag import QueryParser
+
+async def main():
+    parser = QueryParser(schema=Invoice, model_id="gpt-4o")
+    parsed = await parser.async_parse("unpaid invoices from Acme Corp")
+    print(parsed.structured_filters)
+    # → {"paid": {"$eq": false}, "vendor": {"$eq": "Acme Corp"}}
+
+asyncio.run(main())
+```
+
+## API Reference
+
+### `QueryParser`
+
+```python
+QueryParser(
+    schema: type[BaseModel],
+    model_id: str,
+    *,
+    temperature: float = 0.0,
+    max_tokens: int = 1024,
+    **litellm_kwargs,
+)
+```
+
+| Parameter | Type | Description |
+|---|---|---|
+| `schema` | `type[BaseModel]` | Pydantic model whose fields define filterable metadata |
+| `model_id` | `str` | Any LiteLLM-compatible model ID (e.g. `"gpt-4o"`, `"gemini/gemini-2.5-flash"`, `"anthropic/claude-3-opus"`) |
+| `temperature` | `float` | Sampling temperature (default `0.0` for deterministic output) |
+| `max_tokens` | `int` | Maximum tokens to generate (default `1024`) |
+| `**litellm_kwargs` | | Extra kwargs forwarded to `litellm.completion()` (e.g. `api_key`, `api_base`, `timeout`) |
+
+#### Methods
+
+| Method | Signature | Description |
+|---|---|---|
+| `parse` | `(query_text: str) -> ParsedQuery` | Synchronous query parsing |
+| `async_parse` | `(query_text: str) -> ParsedQuery` | Asynchronous query parsing |
+
+#### Properties
+
+| Property | Type | Description |
+|---|---|---|
+| `schema` | `type[BaseModel]` | The Pydantic schema used for field discovery |
+| `model_id` | `str` | The LiteLLM model identifier |
+| `system_prompt` | `str` | The generated system prompt (useful for debugging) |
+
+### `ParsedQuery`
+
+An immutable (frozen) dataclass returned by `parse()` / `async_parse()`.
+
+| Field | Type | Description |
+|---|---|---|
+| `semantic_terms` | `list[str]` | Free-text terms for vector / similarity search |
+| `structured_filters` | `dict[str, Any]` | Metadata filters with MongoDB-style operators |
+| `confidence` | `float` | 0.0 – 1.0 confidence in the parse quality |
+| `explanation` | `str` | Human-readable rationale for the decomposition |
+
+## How It Works
+
+1. **Schema introspection** — `QueryParser` inspects the Pydantic model's fields to identify which ones are scalar/filterable (`int`, `float`, `str`, `bool`, `date`, `datetime`). Complex types like `list[str]` are excluded.
+
+2. **System prompt generation** — A system prompt is built listing the filterable fields with their types and descriptions, instructing the LLM to output a JSON object with `semantic_terms`, `structured_filters`, `confidence`, and `explanation`.
+
+3. **LLM call** — The query text is sent as a user message alongside the system prompt via `litellm.completion()` (sync) or `litellm.acompletion()` (async).
+
+4. **Response parsing** — The LLM's text response is parsed as JSON (handling both raw JSON and Markdown code fences). Values are type-coerced and clamped to produce a valid `ParsedQuery`.
+
+## Supported Filter Operators
+
+The parser instructs the LLM to use MongoDB-style operators:
+
+| Operator | Meaning | Example |
+|---|---|---|
+| `$eq` | Equals | `{"vendor": {"$eq": "Acme"}}` |
+| `$ne` | Not equals | `{"paid": {"$ne": true}}` |
+| `$gt` | Greater than | `{"amount": {"$gt": 1000}}` |
+| `$gte` | Greater than or equal | `{"amount": {"$gte": 5000}}` |
+| `$lt` | Less than | `{"amount": {"$lt": 100}}` |
+| `$lte` | Less than or equal | `{"due_date": {"$lte": "2024-12-31"}}` |
+| `$in` | In list | `{"vendor": {"$in": ["Acme", "Globex"]}}` |
+| `$nin` | Not in list | `{"vendor": {"$nin": ["Initech"]}}` |
+
+## Development
+
+```bash
+# Install dev dependencies
+uv sync
+
+# Run tests
+uv run pytest tests/ -v
+
+# Lint
+uv run ruff check langcore_rag/ tests/
+
+# Format
+uv run ruff format langcore_rag/ tests/
+```
+
+## License
+
+[Apache 2.0](LICENSE)

langcore_rag-1.0.0/langcore_rag/__init__.py

@@ -0,0 +1,14 @@
+"""langcore-rag — RAG query parsing for LangExtract.
+
+Decomposes natural-language queries into semantic terms and
+structured metadata filters using an LLM, enabling hybrid
+vector + metadata retrieval in RAG pipelines.
+"""
+
+from langcore_rag.parser import ParsedQuery, QueryParser
+
+__all__ = [
+    "ParsedQuery",
+    "QueryParser",
+]
+__version__ = "1.0.0"