# LLaVA Completion Pack
This LlamaPack creates the LLaVA multimodal model, and runs its `complete` endpoint to execute queries.
## CLI Usage
You can download llamapacks directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:
```bash
llamaindex-cli download-llamapack LlavaCompletionPack --download-dir ./llava_pack
```
You can then inspect the files at `./llava_pack` and use them as a template for your own project!
## Code Usage
You can download the pack to a `./llava_pack` directory:
```python
from llama_index.core.llama_pack import download_llama_pack
# download and install dependencies
LlavaCompletionPack = download_llama_pack(
"LlavaCompletionPack", "./llava_pack"
)
```
From here, you can use the pack, or inspect and modify the pack in `./llava_pack`.
Then, you can set up the pack like so:
```python
# create the pack
llava_pack = LlavaCompletionPack(image_url="./images/image1.jpg")
```
The `run()` function is a light wrapper around `llm.complete()`.
```python
response = llava_pack.run(
"What dinner can I cook based on the picture of the food in the fridge?"
)
```
You can also use modules individually.
```python
# call the llm.complete()
llm = llava_pack.llm
response = llm.complete("query_str")
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-packs-llava-completion",
"maintainer": "wenqiglantz",
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "image, llava, multimodal",
"author": null,
"author_email": "Your Name <you@example.com>",
"download_url": "https://files.pythonhosted.org/packages/d0/fd/05731aa98900b0611c5dada1450f08136a96f21d42e63e9ff7cfda33ba84/llama_index_packs_llava_completion-0.4.0.tar.gz",
"platform": null,
"description": "# LLaVA Completion Pack\n\nThis LlamaPack creates the LLaVA multimodal model, and runs its `complete` endpoint to execute queries.\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 LlavaCompletionPack --download-dir ./llava_pack\n```\n\nYou can then inspect the files at `./llava_pack` and use them as a template for your own project!\n\n## Code Usage\n\nYou can download the pack to a `./llava_pack` directory:\n\n```python\nfrom llama_index.core.llama_pack import download_llama_pack\n\n# download and install dependencies\nLlavaCompletionPack = download_llama_pack(\n \"LlavaCompletionPack\", \"./llava_pack\"\n)\n```\n\nFrom here, you can use the pack, or inspect and modify the pack in `./llava_pack`.\n\nThen, you can set up the pack like so:\n\n```python\n# create the pack\nllava_pack = LlavaCompletionPack(image_url=\"./images/image1.jpg\")\n```\n\nThe `run()` function is a light wrapper around `llm.complete()`.\n\n```python\nresponse = llava_pack.run(\n \"What dinner can I cook based on the picture of the food in the fridge?\"\n)\n```\n\nYou can also use modules individually.\n\n```python\n# call the llm.complete()\nllm = llava_pack.llm\nresponse = llm.complete(\"query_str\")\n```\n",
"bugtrack_url": null,
"license": null,
"summary": "llama-index packs llava_completion integration",
"version": "0.4.0",
"project_urls": null,
"split_keywords": [
"image",
" llava",
" multimodal"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "4b0088ec3fb7a4d61e7be6bc09c76bc2b1b278a32a857a1337eae0e3b9514a50",
"md5": "c2298b547fa1e67a03c5463225653821",
"sha256": "a4bf9893764da25a8f85ef8a441192dc92bdcfe1ef19184c637b980202df6e89"
},
"downloads": -1,
"filename": "llama_index_packs_llava_completion-0.4.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "c2298b547fa1e67a03c5463225653821",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 3602,
"upload_time": "2025-07-31T00:31:15",
"upload_time_iso_8601": "2025-07-31T00:31:15.623366Z",
"url": "https://files.pythonhosted.org/packages/4b/00/88ec3fb7a4d61e7be6bc09c76bc2b1b278a32a857a1337eae0e3b9514a50/llama_index_packs_llava_completion-0.4.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "d0fd05731aa98900b0611c5dada1450f08136a96f21d42e63e9ff7cfda33ba84",
"md5": "c9129bac983568aa9fdb332df4d3f4c9",
"sha256": "3cd174ee8fb2c4508607e3ae83e32c82bcb5af8f4d3dc0f3c128284fb6a87265"
},
"downloads": -1,
"filename": "llama_index_packs_llava_completion-0.4.0.tar.gz",
"has_sig": false,
"md5_digest": "c9129bac983568aa9fdb332df4d3f4c9",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 3950,
"upload_time": "2025-07-31T00:31:16",
"upload_time_iso_8601": "2025-07-31T00:31:16.340617Z",
"url": "https://files.pythonhosted.org/packages/d0/fd/05731aa98900b0611c5dada1450f08136a96f21d42e63e9ff7cfda33ba84/llama_index_packs_llava_completion-0.4.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-31 00:31:16",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-packs-llava-completion"
}
JSON