# 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/32/8d/c0297a92e8bd7a209354d54d145d04ea4f2feaabcfddcd0ef68556f77f36/llama_index_packs_deeplake_multimodal_retrieval-0.2.0.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": "0.2.0",
"project_urls": null,
"split_keywords": [
"deeplake",
" multimodal",
" retriever"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "021f37affa0a486067986bd16bd8cd232239887d67242e5d498d96c2ad32868e",
"md5": "63d5611b38e40bb597855cc1c873198d",
"sha256": "ef85321b9eeb6ce989b950c03c80a9f5091dd18eae3a27c952bb6d2b52d1c9c5"
},
"downloads": -1,
"filename": "llama_index_packs_deeplake_multimodal_retrieval-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "63d5611b38e40bb597855cc1c873198d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 3383,
"upload_time": "2024-11-18T02:20:50",
"upload_time_iso_8601": "2024-11-18T02:20:50.665933Z",
"url": "https://files.pythonhosted.org/packages/02/1f/37affa0a486067986bd16bd8cd232239887d67242e5d498d96c2ad32868e/llama_index_packs_deeplake_multimodal_retrieval-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "328dc0297a92e8bd7a209354d54d145d04ea4f2feaabcfddcd0ef68556f77f36",
"md5": "f1971f2048dc62f0a485d337c9877b3f",
"sha256": "d2c45bc5965a07ce0c66cb063efc34623527e94cb9cc1a95378b18e90ff57784"
},
"downloads": -1,
"filename": "llama_index_packs_deeplake_multimodal_retrieval-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "f1971f2048dc62f0a485d337c9877b3f",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 2930,
"upload_time": "2024-11-18T02:20:52",
"upload_time_iso_8601": "2024-11-18T02:20:52.268438Z",
"url": "https://files.pythonhosted.org/packages/32/8d/c0297a92e8bd7a209354d54d145d04ea4f2feaabcfddcd0ef68556f77f36/llama_index_packs_deeplake_multimodal_retrieval-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-18 02:20:52",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-packs-deeplake-multimodal-retrieval"
}
JSON