# Recursive Retriever Packs
## Embedded Tables Retriever Pack w/ Unstructured.io
This LlamaPack provides an example of our embedded tables retriever.
This specific template shows the e2e process of building this. It loads
a document, builds a hierarchical node graph (with bigger parent nodes and smaller
child nodes).
Check out the [notebook here](https://github.com/run-llama/llama-hub/blob/main/llama_hub/llama_packs/recursive_retriever/embedded_tables_unstructured/embedded_tables.ipynb).
### CLI Usage
You can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:
```bash
llamaindex-cli download-llamapack EmbeddedTablesUnstructuredRetrieverPack --download-dir ./embedded_tables_unstructured_pack
```
You can then inspect the files at `./embedded_tables_unstructured_pack` and use them as a template for your own project.
### Code Usage
You can download the pack to a the `./embedded_tables_unstructured_pack` directory:
```python
from llama_index.core.llama_pack import download_llama_pack
# download and install dependencies
EmbeddedTablesUnstructuredRetrieverPack = download_llama_pack(
"EmbeddedTablesUnstructuredRetrieverPack",
"./embedded_tables_unstructured_pack",
)
```
From here, you can use the pack, or inspect and modify the pack in `./embedded_tables_unstructured_pack`.
Then, you can set up the pack like so:
```python
# create the pack
# get documents from any data loader
embedded_tables_unstructured_pack = EmbeddedTablesUnstructuredRetrieverPack(
"tesla_2021_10k.htm",
)
```
The `run()` function is a light wrapper around `query_engine.query()`.
```python
response = embedded_tables_unstructured_pack.run(
"What was the revenue in 2020?"
)
```
You can also use modules individually.
```python
# get the node parser
node_parser = embedded_tables_unstructured_pack.node_parser
# get the retriever
retriever = embedded_tables_unstructured_pack.recursive_retriever
# get the query engine
query_engine = embedded_tables_unstructured_pack.query_engine
```
## Recursive Retriever - Small-to-big retrieval
This LlamaPack provides an example of our recursive retriever (small-to-big).
This specific template shows the e2e process of building this. It loads
a document, builds a hierarchical node graph (with bigger parent nodes and smaller
child nodes).
Check out the [notebook here](https://github.com/run-llama/llama-hub/blob/main/llama_hub/llama_packs/recursive_retriever/small_to_big/small_to_big.ipynb).
### CLI Usage
You can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:
```bash
llamaindex-cli download-llamapack RecursiveRetrieverSmallToBigPack --download-dir ./recursive_retriever_stb_pack
```
You can then inspect the files at `./recursive_retriever_stb_pack` and use them as a template for your own project.
### Code Usage
You can download the pack to a the `./recursive_retriever_stb_pack` directory:
```python
from llama_index.core.llama_pack import download_llama_pack
# download and install dependencies
RecursiveRetrieverSmallToBigPack = download_llama_pack(
"RecursiveRetrieverSmallToBigPack", "./recursive_retriever_stb_pack"
)
```
From here, you can use the pack, or inspect and modify the pack in `./recursive_retriever_stb_pack`.
Then, you can set up the pack like so:
```python
# create the pack
# get documents from any data loader
recursive_retriever_stb_pack = RecursiveRetrieverSmallToBigPack(
documents,
)
```
The `run()` function is a light wrapper around `query_engine.query()`.
```python
response = recursive_retriever_stb_pack.run(
"Tell me a bout a Music celebrity."
)
```
You can also use modules individually.
```python
# get the recursive retriever
recursive_retriever = recursive_retriever_stb_pack.recursive_retriever
# get the query engine
query_engine = recursive_retriever_stb_pack.query_engine
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-packs-recursive-retriever",
"maintainer": "jerryjliu",
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "big, embedded, recursive, retriever, small, tables, unstructured",
"author": null,
"author_email": "Your Name <you@example.com>",
"download_url": "https://files.pythonhosted.org/packages/d1/95/05a7f8af176038709a5f2368a94f85e3ac6dcce2aab76a9870255221a9f1/llama_index_packs_recursive_retriever-0.7.0.tar.gz",
"platform": null,
"description": "# Recursive Retriever Packs\n\n## Embedded Tables Retriever Pack w/ Unstructured.io\n\nThis LlamaPack provides an example of our embedded tables retriever.\n\nThis specific template shows the e2e process of building this. It loads\na document, builds a hierarchical node graph (with bigger parent nodes and smaller\nchild nodes).\n\nCheck out the [notebook here](https://github.com/run-llama/llama-hub/blob/main/llama_hub/llama_packs/recursive_retriever/embedded_tables_unstructured/embedded_tables.ipynb).\n\n### CLI Usage\n\nYou can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:\n\n```bash\nllamaindex-cli download-llamapack EmbeddedTablesUnstructuredRetrieverPack --download-dir ./embedded_tables_unstructured_pack\n```\n\nYou can then inspect the files at `./embedded_tables_unstructured_pack` and use them as a template for your own project.\n\n### Code Usage\n\nYou can download the pack to a the `./embedded_tables_unstructured_pack` directory:\n\n```python\nfrom llama_index.core.llama_pack import download_llama_pack\n\n# download and install dependencies\nEmbeddedTablesUnstructuredRetrieverPack = download_llama_pack(\n \"EmbeddedTablesUnstructuredRetrieverPack\",\n \"./embedded_tables_unstructured_pack\",\n)\n```\n\nFrom here, you can use the pack, or inspect and modify the pack in `./embedded_tables_unstructured_pack`.\n\nThen, you can set up the pack like so:\n\n```python\n# create the pack\n# get documents from any data loader\nembedded_tables_unstructured_pack = EmbeddedTablesUnstructuredRetrieverPack(\n \"tesla_2021_10k.htm\",\n)\n```\n\nThe `run()` function is a light wrapper around `query_engine.query()`.\n\n```python\nresponse = embedded_tables_unstructured_pack.run(\n \"What was the revenue in 2020?\"\n)\n```\n\nYou can also use modules individually.\n\n```python\n# get the node parser\nnode_parser = embedded_tables_unstructured_pack.node_parser\n\n# get the retriever\nretriever = embedded_tables_unstructured_pack.recursive_retriever\n\n# get the query engine\nquery_engine = embedded_tables_unstructured_pack.query_engine\n```\n\n## Recursive Retriever - Small-to-big retrieval\n\nThis LlamaPack provides an example of our recursive retriever (small-to-big).\n\nThis specific template shows the e2e process of building this. It loads\na document, builds a hierarchical node graph (with bigger parent nodes and smaller\nchild nodes).\n\nCheck out the [notebook here](https://github.com/run-llama/llama-hub/blob/main/llama_hub/llama_packs/recursive_retriever/small_to_big/small_to_big.ipynb).\n\n### CLI Usage\n\nYou can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:\n\n```bash\nllamaindex-cli download-llamapack RecursiveRetrieverSmallToBigPack --download-dir ./recursive_retriever_stb_pack\n```\n\nYou can then inspect the files at `./recursive_retriever_stb_pack` and use them as a template for your own project.\n\n### Code Usage\n\nYou can download the pack to a the `./recursive_retriever_stb_pack` directory:\n\n```python\nfrom llama_index.core.llama_pack import download_llama_pack\n\n# download and install dependencies\nRecursiveRetrieverSmallToBigPack = download_llama_pack(\n \"RecursiveRetrieverSmallToBigPack\", \"./recursive_retriever_stb_pack\"\n)\n```\n\nFrom here, you can use the pack, or inspect and modify the pack in `./recursive_retriever_stb_pack`.\n\nThen, you can set up the pack like so:\n\n```python\n# create the pack\n# get documents from any data loader\nrecursive_retriever_stb_pack = RecursiveRetrieverSmallToBigPack(\n documents,\n)\n```\n\nThe `run()` function is a light wrapper around `query_engine.query()`.\n\n```python\nresponse = recursive_retriever_stb_pack.run(\n \"Tell me a bout a Music celebrity.\"\n)\n```\n\nYou can also use modules individually.\n\n```python\n# get the recursive retriever\nrecursive_retriever = recursive_retriever_stb_pack.recursive_retriever\n\n# get the query engine\nquery_engine = recursive_retriever_stb_pack.query_engine\n```\n",
"bugtrack_url": null,
"license": null,
"summary": "llama-index packs recursive_retriever integration",
"version": "0.7.0",
"project_urls": null,
"split_keywords": [
"big",
" embedded",
" recursive",
" retriever",
" small",
" tables",
" unstructured"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "37614334d7b6d6b455241a3130a51b2c1099222d50dc40114280cdd5d588f646",
"md5": "f8f111046e6e1ed03c4f3ba64d7158d2",
"sha256": "ecff55c0bcc7d3ba36dba73d20f6d6aca6d61bdb2580489de3bcbb0744a71862"
},
"downloads": -1,
"filename": "llama_index_packs_recursive_retriever-0.7.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "f8f111046e6e1ed03c4f3ba64d7158d2",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 6479,
"upload_time": "2025-07-31T03:01:05",
"upload_time_iso_8601": "2025-07-31T03:01:05.030756Z",
"url": "https://files.pythonhosted.org/packages/37/61/4334d7b6d6b455241a3130a51b2c1099222d50dc40114280cdd5d588f646/llama_index_packs_recursive_retriever-0.7.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d19505a7f8af176038709a5f2368a94f85e3ac6dcce2aab76a9870255221a9f1",
"md5": "7dec1a23717a7ec8c052721610d864c6",
"sha256": "28e08f665bab3916fd7b517ba416e2292dee6f6fc9b18dee84a19a53a3eb3906"
},
"downloads": -1,
"filename": "llama_index_packs_recursive_retriever-0.7.0.tar.gz",
"has_sig": false,
"md5_digest": "7dec1a23717a7ec8c052721610d864c6",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 5742,
"upload_time": "2025-07-31T03:01:06",
"upload_time_iso_8601": "2025-07-31T03:01:06.075739Z",
"url": "https://files.pythonhosted.org/packages/d1/95/05a7f8af176038709a5f2368a94f85e3ac6dcce2aab76a9870255221a9f1/llama_index_packs_recursive_retriever-0.7.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-31 03:01:06",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-packs-recursive-retriever"
}
JSON