# DeepLake DeepMemory Pack
This LlamaPack inserts your multimodal data (texts, images) into deeplake and instantiates an deeplake retriever, which will use clip for embedding images and GPT4-V during runtime.
## CLI Usage
You can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:
```bash
llamaindex-cli download-llamapack DeepLakeMultimodalRetrieverPack --download-dir ./deeplake_multimodal_pack
```
You can then inspect the files at `./deeplake_multimodal_pack` and use them as a template for your own project!
## Code Usage
You can download the pack to a `./deeplake_multimodal_pack` directory:
```python
from llama_index.core.llama_pack import download_llama_pack
# download and install dependencies
DeepLakeMultimodalRetriever = download_llama_pack(
"DeepLakeMultimodalRetrieverPack", "./deeplake_multimodal_pack"
)
```
From here, you can use the pack, or inspect and modify the pack in `./deepmemory_pack`.
Then, you can set up the pack like so:
```python
# setup pack arguments
from llama_index.core.vector_stores import MetadataInfo, VectorStoreInfo
# collection of image and text nodes
nodes = [...]
# create the pack
deeplake_pack = DeepLakeMultimodalRetriever(
nodes=nodes, dataset_path="llama_index", overwrite=False
)
```
The `run()` function is a light wrapper around `SimpleMultiModalQueryEngine`.
```python
response = deeplake_pack.run("Tell me a bout a Music celebritiy.")
```
You can also use modules individually.
```python
# use the retriever
retriever = deeplake_pack.retriever
nodes = retriever.retrieve("query_str")
# use the query engine
query_engine = deeplake_pack.query_engine
response = query_engine.query("query_str")
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-packs-deeplake-multimodal-retrieval",
"maintainer": "AdkSarsen",
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "deeplake, multimodal, retriever",
"author": "Your Name",
"author_email": "you@example.com",
"download_url": "https://files.pythonhosted.org/packages/15/d7/99d0c4e6a7cff9531c88f9b3aeecfe1ac0ddd383370ebdae0776af00890a/llama_index_packs_deeplake_multimodal_retrieval-0.1.4.tar.gz",
"platform": null,
"description": "# DeepLake DeepMemory Pack\n\nThis LlamaPack inserts your multimodal data (texts, images) into deeplake and instantiates an deeplake retriever, which will use clip for embedding images and GPT4-V during runtime.\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 DeepLakeMultimodalRetrieverPack --download-dir ./deeplake_multimodal_pack\n```\n\nYou can then inspect the files at `./deeplake_multimodal_pack` and use them as a template for your own project!\n\n## Code Usage\n\nYou can download the pack to a `./deeplake_multimodal_pack` directory:\n\n```python\nfrom llama_index.core.llama_pack import download_llama_pack\n\n# download and install dependencies\nDeepLakeMultimodalRetriever = download_llama_pack(\n \"DeepLakeMultimodalRetrieverPack\", \"./deeplake_multimodal_pack\"\n)\n```\n\nFrom here, you can use the pack, or inspect and modify the pack in `./deepmemory_pack`.\n\nThen, you can set up the pack like so:\n\n```python\n# setup pack arguments\nfrom llama_index.core.vector_stores import MetadataInfo, VectorStoreInfo\n\n# collection of image and text nodes\nnodes = [...]\n\n# create the pack\ndeeplake_pack = DeepLakeMultimodalRetriever(\n nodes=nodes, dataset_path=\"llama_index\", overwrite=False\n)\n```\n\nThe `run()` function is a light wrapper around `SimpleMultiModalQueryEngine`.\n\n```python\nresponse = deeplake_pack.run(\"Tell me a bout a Music celebritiy.\")\n```\n\nYou can also use modules individually.\n\n```python\n# use the retriever\nretriever = deeplake_pack.retriever\nnodes = retriever.retrieve(\"query_str\")\n\n# use the query engine\nquery_engine = deeplake_pack.query_engine\nresponse = query_engine.query(\"query_str\")\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index packs deeplake_multimodal_retrieval integration",
"version": "0.1.4",
"project_urls": null,
"split_keywords": [
"deeplake",
" multimodal",
" retriever"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9f4532ee1233604db528840aa548e31cc3deb5067c8c1d64bb4ec46a620e5a2b",
"md5": "139bdd4ba4b3ce216e82d08294fc22fc",
"sha256": "32d9aeaf0c8a5c968ee2e1c6dd925ad6241ea0783c1e1897bffce950f30515a1"
},
"downloads": -1,
"filename": "llama_index_packs_deeplake_multimodal_retrieval-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "139bdd4ba4b3ce216e82d08294fc22fc",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 3381,
"upload_time": "2024-08-06T00:44:02",
"upload_time_iso_8601": "2024-08-06T00:44:02.522167Z",
"url": "https://files.pythonhosted.org/packages/9f/45/32ee1233604db528840aa548e31cc3deb5067c8c1d64bb4ec46a620e5a2b/llama_index_packs_deeplake_multimodal_retrieval-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "15d799d0c4e6a7cff9531c88f9b3aeecfe1ac0ddd383370ebdae0776af00890a",
"md5": "cfb5ee2cd82bd44bdf935f8e8d0479e5",
"sha256": "92e3f0a10ece7f561c2d90814cfa4a788372dacce70ce5ab18883aa87ef5b0b5"
},
"downloads": -1,
"filename": "llama_index_packs_deeplake_multimodal_retrieval-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "cfb5ee2cd82bd44bdf935f8e8d0479e5",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 2886,
"upload_time": "2024-08-06T00:44:03",
"upload_time_iso_8601": "2024-08-06T00:44:03.870883Z",
"url": "https://files.pythonhosted.org/packages/15/d7/99d0c4e6a7cff9531c88f9b3aeecfe1ac0ddd383370ebdae0776af00890a/llama_index_packs_deeplake_multimodal_retrieval-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-08-06 00:44:03",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-packs-deeplake-multimodal-retrieval"
}
JSON