cocoindex 0.1.25__tar.gz → 0.1.26__tar.gz

{cocoindex-0.1.25 → cocoindex-0.1.26}/.github/ISSUE_TEMPLATE//360/237/222/241-feature-request.md

@@ -18,3 +18,7 @@ A clear and concise description of any alternative solutions or features you've
 
 **Additional context**
 Add any other context or screenshots about the feature request here.
+
+---
+[Contributing Guide](https://cocoindex.io/docs/about/contributing)
+For changes that takes more than a day, we recommend you to leave a comment on the issue like **`I'm working on it`**  or **`Can I work on this issue?`** to avoid duplicating work.

{cocoindex-0.1.25 → cocoindex-0.1.26}/Cargo.lock

@@ -224,9 +224,9 @@ dependencies = [
 
 [[package]]
 name = "aws-lc-sys"
-version = "0.28.1"
+version = "0.28.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0ddeb19ee86cb16ecfc871e5b0660aff6285760957aaedda6284cf0e790d3769"
+checksum = "bfa9b6986f250236c27e5a204062434a773a13243d2ffc2955f37bdba4c5c6a1"
 dependencies = [
  "bindgen",
  "cc",
@@ -321,7 +321,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b62ddb9cb1ec0a098ad4bbf9344d0713fa193ae1a80af55febcff2627b6a00c1"
 dependencies = [
  "futures-core",
- "getrandom 0.2.15",
+ "getrandom 0.2.16",
  "instant",
  "pin-project-lite",
  "rand 0.8.5",
@@ -533,7 +533,7 @@ dependencies = [
 
 [[package]]
 name = "cocoindex"
-version = "0.1.25"
+version = "0.1.26"
 dependencies = [
  "anyhow",
  "async-openai",
@@ -708,7 +708,7 @@ version = "0.1.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f9d839f2a20b0aee515dc581a6172f2321f96cab76c1a38a4c584a194955390e"
 dependencies = [
- "getrandom 0.2.15",
+ "getrandom 0.2.16",
  "once_cell",
  "tiny-keccak",
 ]
@@ -1281,9 +1281,9 @@ dependencies = [
 
 [[package]]
 name = "getrandom"
-version = "0.2.15"
+version = "0.2.16"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c4567c8db10ae91089c99af84c68c38da3ec2f087c3f82960bcdbf3656b6f4d7"
+checksum = "335ff9f135e4384c8150d6f27c6daed433577f86b4750418338c01a1a2528592"
 dependencies = [
  "cfg-if",
  "js-sys",
@@ -1881,9 +1881,9 @@ checksum = "4a5f13b858c8d314ee3e8f639011f7ccefe71f97f96e50151fb991f267928e2c"
 
 [[package]]
 name = "jiff"
-version = "0.2.9"
+version = "0.2.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "59ec30f7142be6fe14e1b021f50b85db8df2d4324ea6e91ec3e5dcde092021d0"
+checksum = "5a064218214dc6a10fbae5ec5fa888d80c45d611aba169222fc272072bf7aef6"
 dependencies = [
  "jiff-static",
  "log",
@@ -1894,9 +1894,9 @@ dependencies = [
 
 [[package]]
 name = "jiff-static"
-version = "0.2.9"
+version = "0.2.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "526b834d727fd59d37b076b0c3236d9adde1b1729a4361e20b2026f738cc1dbe"
+checksum = "199b7932d97e325aff3a7030e141eafe7f2c6268e1d1b24859b753a627f45254"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -1967,9 +1967,9 @@ dependencies = [
 
 [[package]]
 name = "libm"
-version = "0.2.11"
+version = "0.2.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8355be11b20d696c8f18f6cc018c4e372165b1fa8126cef092399c9951984ffa"
+checksum = "c9627da5196e5d8ed0b0495e61e518847578da83483c37288316d9b2e03a7f72"
 
 [[package]]
 name = "libsqlite3-sys"
@@ -2570,9 +2570,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3"
-version = "0.24.1"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "17da310086b068fbdcefbba30aeb3721d5bb9af8db4987d6735b2183ca567229"
+checksum = "e5203598f366b11a02b13aa20cab591229ff0a89fd121a308a5df751d5fc9219"
 dependencies = [
  "cfg-if",
  "chrono",
@@ -2602,9 +2602,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-build-config"
-version = "0.24.1"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e27165889bd793000a098bb966adc4300c312497ea25cf7a690a9f0ac5aa5fc1"
+checksum = "99636d423fa2ca130fa5acde3059308006d46f98caac629418e53f7ebb1e9999"
 dependencies = [
  "once_cell",
  "target-lexicon",
@@ -2612,9 +2612,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-ffi"
-version = "0.24.1"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "05280526e1dbf6b420062f3ef228b78c0c54ba94e157f5cb724a609d0f2faabc"
+checksum = "78f9cf92ba9c409279bc3305b5409d90db2d2c22392d443a87df3a1adad59e33"
 dependencies = [
  "libc",
  "pyo3-build-config",
@@ -2622,9 +2622,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros"
-version = "0.24.1"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c3ce5686aa4d3f63359a5100c62a127c9f15e8398e5fdeb5deef1fed5cd5f44"
+checksum = "0b999cb1a6ce21f9a6b147dcf1be9ffedf02e0043aec74dc390f3007047cecd9"
 dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
@@ -2634,9 +2634,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros-backend"
-version = "0.24.1"
+version = "0.24.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f4cf6faa0cbfb0ed08e89beb8103ae9724eb4750e3a78084ba4017cbe94f3855"
+checksum = "822ece1c7e1012745607d5cf0bcb2874769f0f7cb34c4cde03b9358eb9ef911a"
 dependencies = [
  "heck",
  "proc-macro2",
@@ -2657,9 +2657,9 @@ dependencies = [
 
 [[package]]
 name = "qdrant-client"
-version = "1.13.0"
+version = "1.14.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9b585625d1ef06478e97fe8d7170a3f32a1cba5dbf986ff136095a85a0ec3d91"
+checksum = "f7b17bc17a707188d378d8643af36c499b7a3c8ece72c9341d7eff4c1eb49a33"
 dependencies = [
  "anyhow",
  "derive_builder",
@@ -2698,9 +2698,9 @@ dependencies = [
 
 [[package]]
 name = "quinn-proto"
-version = "0.11.10"
+version = "0.11.11"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b820744eb4dc9b57a3398183639c511b5a26d2ed702cedd3febaa1393caa22cc"
+checksum = "bcbafbbdbb0f638fe3f35f3c56739f77a8a1d070cb25603226c83339b391472b"
 dependencies = [
  "bytes",
  "getrandom 0.3.2",
@@ -2792,7 +2792,7 @@ version = "0.6.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ec0be4795e2f6a28069bec0b5ff3e2ac9bafc99e6a9a7dc3547996c5c816922c"
 dependencies = [
- "getrandom 0.2.15",
+ "getrandom 0.2.16",
 ]
 
 [[package]]
@@ -2935,7 +2935,7 @@ checksum = "a4689e6c2294d81e88dc6261c768b63bc4fcdb852be6d1352498b114f61383b7"
 dependencies = [
  "cc",
  "cfg-if",
- "getrandom 0.2.15",
+ "getrandom 0.2.16",
  "libc",
  "untrusted",
  "windows-sys 0.52.0",
@@ -3364,9 +3364,9 @@ checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
 
 [[package]]
 name = "signal-hook-registry"
-version = "1.4.4"
+version = "1.4.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a1ee1aca2bc74ef9589efa7ccaa0f3752751399940356209b3fd80c078149b5e"
+checksum = "9203b8055f63a2a00e2f593bb0510367fe707d7ff1e5c872de2f537b339e5410"
 dependencies = [
  "libc",
 ]
@@ -3897,9 +3897,9 @@ dependencies = [
 
 [[package]]
 name = "tokio-util"
-version = "0.7.14"
+version = "0.7.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6b9590b93e6fcc1739458317cccd391ad3955e2bde8913edf6f95f9e65a8f034"
+checksum = "66a539a9ad6d5d281510d5bd368c973d636c02dbf8a67300bfb6b950696ad7df"
 dependencies = [
  "bytes",
  "futures-core",

{cocoindex-0.1.25 → cocoindex-0.1.26}/Cargo.toml

@@ -2,7 +2,7 @@
 name = "cocoindex"
 # Version used for local development is always higher than others to take precedence.
 # Will be overridden for specific release versions.
-version = "0.1.25"
+version = "0.1.26"
 edition = "2021"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html

{cocoindex-0.1.25 → cocoindex-0.1.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cocoindex
-Version: 0.1.25
+Version: 0.1.26
 Requires-Dist: sentence-transformers>=3.3.1
 Requires-Dist: click>=8.1.8
 Requires-Dist: pytest ; extra == 'test'
@@ -117,7 +117,7 @@ Go to the [examples directory](examples) to try out with any of the examples, fo
 | [PDF Embedding](examples/pdf_embedding) | Parse PDF and index text embeddings for semantic search |
 | [Manuals LLM Extraction](examples/manuals_llm_extraction) | Extract structured information from a manual using LLM |
 | [Google Drive Text Embedding](examples/gdrive_text_embedding) | Index text documents from Google Drive |
-| [Docs to Knowledge Graph](examples/docs_to_kg) | Extract relationships from Markdown documents and build a knowledge graph |
+| [Docs to Knowledge Graph](examples/docs_to_knowledge_graph) | Extract relationships from Markdown documents and build a knowledge graph |
 | [Embeddings to Qdrant](examples/text_embedding_qdrant) | Index documents in a Qdrant collection for semantic search |
 
 More coming and stay tuned! If there's any specific examples you would like to see, please let us know in our [Discord community](https://discord.com/invite/zpA9S2DR7s) 🌱.

{cocoindex-0.1.25 → cocoindex-0.1.26}/README.md

@@ -102,7 +102,7 @@ Go to the [examples directory](examples) to try out with any of the examples, fo
 | [PDF Embedding](examples/pdf_embedding) | Parse PDF and index text embeddings for semantic search |
 | [Manuals LLM Extraction](examples/manuals_llm_extraction) | Extract structured information from a manual using LLM |
 | [Google Drive Text Embedding](examples/gdrive_text_embedding) | Index text documents from Google Drive |
-| [Docs to Knowledge Graph](examples/docs_to_kg) | Extract relationships from Markdown documents and build a knowledge graph |
+| [Docs to Knowledge Graph](examples/docs_to_knowledge_graph) | Extract relationships from Markdown documents and build a knowledge graph |
 | [Embeddings to Qdrant](examples/text_embedding_qdrant) | Index documents in a Qdrant collection for semantic search |
 
 More coming and stay tuned! If there's any specific examples you would like to see, please let us know in our [Discord community](https://discord.com/invite/zpA9S2DR7s) 🌱.

{cocoindex-0.1.25 → cocoindex-0.1.26}/docs/docs/about/community.md

@@ -29,7 +29,7 @@ Join our community channels to get help, share ideas, and connect with other dev
 
 Need help? Here are the best ways to get support:
 
-- Email us at [support@cocoindex.io](mailto:support@cocoindex.io)
+- Email us at [hi@cocoindex.io](mailto:hi@cocoindex.io)
 - Check our [documentation](https://cocoindex.io/docs)
 - Read our [blog posts](https://cocoindex.io/blogs)
-- Ask questions in our Discord community 
+- Ask questions in our [Discord Server](https://discord.com/invite/zpA9S2DR7s)

{cocoindex-0.1.25 → cocoindex-0.1.26}/docs/docs/about/contributing.md

@@ -5,9 +5,23 @@ description: Learn how to contribute to CocoIndex
 
 # Contributing
 
-We love contributions from our community! This guide explains how to get involved and contribute to CocoIndex.
+[CocoIndex](https://github.com/cocoindex-io/cocoindex) is an open source project. We are respectful, open and friendly. This guide explains how to get involved and contribute to [CocoIndex](https://github.com/cocoindex-io/cocoindex).
 
-## Setting Up Development Environment
+## Issues:
+
+We use [GitHub Issues](https://github.com/cocoindex-io/cocoindex/issues) to track bugs and feature requests.
+
+## Good First Issues
+
+We tag issues with the ["good first issue"](https://github.com/cocoindex-io/cocoindex/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) label for beginner contributors.
+
+## How to Contribute 
+- If you decide to work on an issue, unless the PR can be sent immediately (e.g. just a few lines of code), we recommend you to leave a comment on the issue like **`I'm working on it`**  or **`Can I work on this issue?`** to avoid duplicating work.
+- For larger features, we recommend you to discuss with us first in our [Discord server](https://discord.com/invite/zpA9S2DR7s) to coordinate the design and work.
+- Our [Discord server](https://discord.com/invite/zpA9S2DR7s) are constantly open. If you are unsure about anything, it is a good place to discuss! We'd love to collaborate and will always be friendly.
+
+## Start hacking! Setting Up Development Environment 
+Following the steps below to get cocoindex build on latest codebase locally - if you are making changes to cocoindex funcionality and want to test it out.
 
 -   Install Rust toolchain: [docs](https://rust-lang.org/tools/install)
 
@@ -48,7 +62,6 @@ To submit your code:
 In your PR description, please include:
 - Description of the changes
 - Motivation and context
-- Test coverage details
 - Note if it's a breaking change
 - Reference any related GitHub issues
 

{cocoindex-0.1.25 → cocoindex-0.1.26}/docs/docs/ai/llm.mdx

@@ -21,7 +21,7 @@ It has the following fields:
 *   `address` (optional): The address of the LLM API.
 
 
-## LLM API integrations
+## LLM API Integrations
 
 CocoIndex integrates with various LLM APIs for these functions.
 
@@ -77,3 +77,24 @@ cocoindex.LlmSpec(
 </TabItem>
 </Tabs>
 
+### Google Gemini
+
+To use the Gemini LLM API, you need to set the environment variable `GEMINI_API_KEY`.
+You can generate the API key from [Google AI Studio](https://aistudio.google.com/apikey).
+
+A spec for Gemini looks like this:
+
+<Tabs>
+<TabItem value="python" label="Python" default>
+
+```python
+cocoindex.LlmSpec(
+    api_type=cocoindex.LlmApiType.GEMINI,
+    model="gemini-2.0-flash",
+)
+```
+
+</TabItem>
+</Tabs>
+
+You can find the full list of models supported by Gemini [here](https://ai.google.dev/gemini-api/docs/models).

{cocoindex-0.1.25/examples/docs_to_kg → cocoindex-0.1.26/examples/docs_to_knowledge_graph}/main.py

@@ -92,6 +92,7 @@ def docs_to_kg_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoindex.D
                     id=cocoindex.GeneratedField.UUID, entity=relationship["object"],
                     filename=doc["filename"], location=chunk["location"],
                 )
+
     document_node.export(
         "document_node",
         cocoindex.storages.Neo4j(
@@ -99,6 +100,23 @@ def docs_to_kg_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoindex.D
             mapping=cocoindex.storages.NodeMapping(label="Document")),
         primary_key_fields=["filename"],
     )
+    flow_builder.declare(
+        cocoindex.storages.Neo4jDeclarations(
+            connection=conn_spec,
+            referenced_nodes=[
+                cocoindex.storages.ReferencedNode(
+                    label="Entity",
+                    primary_key_fields=["value"],
+                    vector_indexes=[
+                        cocoindex.VectorIndexDef(
+                            field_name="embedding",
+                            metric=cocoindex.VectorSimilarityMetric.COSINE_SIMILARITY,
+                        ),
+                    ],
+                )
+            ]
+        )
+    )
     entity_relationship.export(
         "entity_relationship",
         cocoindex.storages.Neo4j(
@@ -123,17 +141,6 @@ def docs_to_kg_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoindex.D
                             source="object_embedding", target="embedding"),
                     ]
                 ),
-                nodes_storage_spec={
-                    "Entity": cocoindex.storages.NodeStorageSpec(
-                        primary_key_fields=["value"],
-                        vector_indexes=[
-                            cocoindex.VectorIndexDef(
-                                field_name="embedding",
-                                metric=cocoindex.VectorSimilarityMetric.COSINE_SIMILARITY,
-                            ),
-                        ],
-                    ),
-                },
             ),
         ),
         primary_key_fields=["id"],

{cocoindex-0.1.25 → cocoindex-0.1.26}/examples/gdrive_text_embedding/main.py

@@ -1,5 +1,6 @@
 from dotenv import load_dotenv
 
+import asyncio
 import cocoindex
 import datetime
 import os
@@ -73,5 +74,4 @@ async def _run():
 
 if __name__ == "__main__":
     load_dotenv(override=True)
-    import asyncio
     asyncio.run(_run())

{cocoindex-0.1.25 → cocoindex-0.1.26}/examples/manuals_llm_extraction/main.py

@@ -90,9 +90,14 @@ def manual_extraction_flow(flow_builder: cocoindex.FlowBuilder, data_scope: coco
                      # See the full list of models: https://ollama.com/library
                      model="llama3.2"
                 ),
+
                 # Replace by this spec below, to use OpenAI API model instead of ollama
                 #   llm_spec=cocoindex.LlmSpec(
                 #       api_type=cocoindex.LlmApiType.OPENAI, model="gpt-4o"),
+
+                # Replace by this spec below, to use Gemini API model
+                #   llm_spec=cocoindex.LlmSpec(
+                #       api_type=cocoindex.LlmApiType.GEMINI, model="gemini-2.0-flash"),
                 output_type=ModuleInfo,
                 instruction="Please extract Python module information from the manual."))
         doc["module_summary"] = doc["module_info"].transform(summarize_module)

{cocoindex-0.1.25 → cocoindex-0.1.26}/examples/text_embedding/README.md

@@ -1,6 +1,9 @@
 Simple example for cocoindex: build embedding index based on local files.
 
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/cocoindex-io/cocoindex/blob/main/examples/text_embedding/Text_Embedding.ipynb)
+
 ## Prerequisite
+
 [Install Postgres](https://cocoindex.io/docs/getting_started/installation#-install-postgres) if you don't have one.
 
 ## Run
@@ -29,7 +32,8 @@ Run:
 python main.py
 ```
 
-## CocoInsight 
+## CocoInsight
+
 CocoInsight is in Early Access now (Free) 😊 You found us! A quick 3 minute video tutorial about CocoInsight: [Watch on YouTube](https://youtu.be/ZnmyoHslBSc?si=pPLXWALztkA710r9).
 
 Run CocoInsight to understand your RAG data pipeline:
@@ -38,4 +42,5 @@ Run CocoInsight to understand your RAG data pipeline:
 python main.py cocoindex server -c https://cocoindex.io
 ```
 
-Then open the CocoInsight UI at [https://cocoindex.io/cocoinsight](https://cocoindex.io/cocoinsight).
+Then open the CocoInsight UI at [https://cocoindex.io/cocoinsight](https://cocoindex.io/cocoinsight).
+