# Vectara RAG Pack
This LlamaPack provides an end-to-end Retrieval Augmented Generation flow using Vectara.
Please note that this guide is only relevant for versions >= 0.4.0
To use the Vectara RAG Pack, you will need a Vectara account. If you don't have one already, you can [sign up](https://vectara.com/integrations/llamaindex)
and follow our [Quick Start](https://docs.vectara.com/docs/quickstart) guide to create a corpus and an API key (make sure it has both indexing and query permissions).
You can then configure your environment or provide the following arguments directly when initializing your VectaraIndex:
```
VECTARA_CORPUS_KEY=your_corpus_key
VECTARA_API_KEY=your-vectara-api-key
```
## CLI Usage
You can download the Vectara llamapack directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:
```bash
llamaindex-cli download-llamapack VectaraRagPack --download-dir ./vectara_rag_pack
```
Feel free to inspect the files at `./vectara_rag_pack` and use them as a template for your own project!
## Code Usage
You can download the pack to a `./vectara_rag_pack` directory:
```python
from llama_index.core.llama_pack import download_llama_pack
VectaraRAG = download_llama_pack("VectaraRagPack", "./vectara_rag_pack")
```
Then, you can set up the pack in two ways:
1. If you want to ingest documents into the Vectara Corpus:
```python
nodes = [...]
vectara = VectaraRAG(nodes=nodes)
```
2. If you already indexed data on Vectara, and just want to use the retrieval/query functionality:
```python
vectara = VectaraRAG()
```
Additional optional arguments to VectaraRAG:
- `similarity_top_k`: determines the number of results to return. Defaults to 5.
- `lambda_val`: a value between 0 and 1 to specify hybrid search,
determines the balance between pure neural search (0) and keyword matching (1).
- `n_sentences_before` and `n_sentences_after`: determine the number of sentences before/after the
matching fact to use with the summarization LLM. defaults to 2.
- `reranker`: 'none', 'mmr', 'multilingual_reranker_v1', 'userfn', or 'chain'
The reranker name 'slingshot' is the same as 'multilingual_reranker_v1' (backwards compatible)
- `rerank_k`: the number of results to use for reranking, defaults to 50.
- `mmr_diversity_bias`: when using the mmr reranker, determines the degree
of diversity among the results with 0 corresponding
to minimum diversity and 1 to maximum diversity. Defaults to 0.3.
- `udf_expression`: when using the udf reranker, specifies the user expression for reranking results.
- `rerank_chain`: when using the chain reranker, specifies a list of rerankers to be applied
in a sequence and their associated parameters.
- `summary_enabled`: whether to generate summaries or not. Defaults to True.
- When summary_enabled is True, you can set the following:
- `summary_response_lang`: language to use (ISO 639-2 code) for summary generation. defaults to "eng".
- `summary_num_results`: number of results to use for summary generation. Defaults to 7.
- `summary_prompt_name`: name of the prompt to use for summary generation.
Defaults to 'vectara-summary-ext-24-05-sml'.
For example to use maximal diversity with MMR:
```python
vectara = VectaraRAG(reranker="mmr", rerank_k=50, mmr_diversity_bias=1.0)
```
Or if you want to include more results in the Vectara generated summarization you can try:
```python
vectara = VectaraRAG(summary_num_results=12)
```
Once you have the Vectara RAG object, you can now use it as a retriever:
```python
# use the retriever
nodes = vectara.retrieve("Is light a wave or a particle?")
```
Or as a query engine (with Vectara summarization call):
```python
# use the query engine
response = vectara._query_engine.query(
"Is light a wave or a particle?"
).response
```
Note that the `run()` function is a light wrapper around `query_engine.query()`.
```python
response = vectara.run("Is light a wave or a particle?").response
```
Enjoy your Vectara RAG pack!
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-packs-vectara-rag",
"maintainer": "ofermend",
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "embeddings, rag, retrieval, vectara",
"author": null,
"author_email": "Your Name <you@example.com>",
"download_url": "https://files.pythonhosted.org/packages/7a/bc/f0df151021c5f781ef6e48231f9c2785a41df78ce47f9c812a36b9e427dc/llama_index_packs_vectara_rag-0.5.0.tar.gz",
"platform": null,
"description": "# Vectara RAG Pack\n\nThis LlamaPack provides an end-to-end Retrieval Augmented Generation flow using Vectara.\nPlease note that this guide is only relevant for versions >= 0.4.0\n\nTo use the Vectara RAG Pack, you will need a Vectara account. If you don't have one already, you can [sign up](https://vectara.com/integrations/llamaindex)\nand follow our [Quick Start](https://docs.vectara.com/docs/quickstart) guide to create a corpus and an API key (make sure it has both indexing and query permissions).\n\nYou can then configure your environment or provide the following arguments directly when initializing your VectaraIndex:\n\n```\nVECTARA_CORPUS_KEY=your_corpus_key\nVECTARA_API_KEY=your-vectara-api-key\n```\n\n## CLI Usage\n\nYou can download the Vectara llamapack directly using `llamaindex-cli`, which comes installed with the `llama-index` python package:\n\n```bash\nllamaindex-cli download-llamapack VectaraRagPack --download-dir ./vectara_rag_pack\n```\n\nFeel free to inspect the files at `./vectara_rag_pack` and use them as a template for your own project!\n\n## Code Usage\n\nYou can download the pack to a `./vectara_rag_pack` directory:\n\n```python\nfrom llama_index.core.llama_pack import download_llama_pack\n\nVectaraRAG = download_llama_pack(\"VectaraRagPack\", \"./vectara_rag_pack\")\n```\n\nThen, you can set up the pack in two ways:\n\n1. If you want to ingest documents into the Vectara Corpus:\n\n```python\nnodes = [...]\nvectara = VectaraRAG(nodes=nodes)\n```\n\n2. If you already indexed data on Vectara, and just want to use the retrieval/query functionality:\n\n```python\nvectara = VectaraRAG()\n```\n\nAdditional optional arguments to VectaraRAG:\n\n- `similarity_top_k`: determines the number of results to return. Defaults to 5.\n- `lambda_val`: a value between 0 and 1 to specify hybrid search,\n determines the balance between pure neural search (0) and keyword matching (1).\n- `n_sentences_before` and `n_sentences_after`: determine the number of sentences before/after the\n matching fact to use with the summarization LLM. defaults to 2.\n- `reranker`: 'none', 'mmr', 'multilingual_reranker_v1', 'userfn', or 'chain'\n The reranker name 'slingshot' is the same as 'multilingual_reranker_v1' (backwards compatible)\n- `rerank_k`: the number of results to use for reranking, defaults to 50.\n- `mmr_diversity_bias`: when using the mmr reranker, determines the degree\n of diversity among the results with 0 corresponding\n to minimum diversity and 1 to maximum diversity. Defaults to 0.3.\n- `udf_expression`: when using the udf reranker, specifies the user expression for reranking results.\n- `rerank_chain`: when using the chain reranker, specifies a list of rerankers to be applied\n in a sequence and their associated parameters.\n- `summary_enabled`: whether to generate summaries or not. Defaults to True.\n- When summary_enabled is True, you can set the following:\n - `summary_response_lang`: language to use (ISO 639-2 code) for summary generation. defaults to \"eng\".\n - `summary_num_results`: number of results to use for summary generation. Defaults to 7.\n - `summary_prompt_name`: name of the prompt to use for summary generation.\n Defaults to 'vectara-summary-ext-24-05-sml'.\n\nFor example to use maximal diversity with MMR:\n\n```python\nvectara = VectaraRAG(reranker=\"mmr\", rerank_k=50, mmr_diversity_bias=1.0)\n```\n\nOr if you want to include more results in the Vectara generated summarization you can try:\n\n```python\nvectara = VectaraRAG(summary_num_results=12)\n```\n\nOnce you have the Vectara RAG object, you can now use it as a retriever:\n\n```python\n# use the retriever\nnodes = vectara.retrieve(\"Is light a wave or a particle?\")\n```\n\nOr as a query engine (with Vectara summarization call):\n\n```python\n# use the query engine\nresponse = vectara._query_engine.query(\n \"Is light a wave or a particle?\"\n).response\n```\n\nNote that the `run()` function is a light wrapper around `query_engine.query()`.\n\n```python\nresponse = vectara.run(\"Is light a wave or a particle?\").response\n```\n\nEnjoy your Vectara RAG pack!\n",
"bugtrack_url": null,
"license": null,
"summary": "llama-index packs vectara_rag integration",
"version": "0.5.0",
"project_urls": null,
"split_keywords": [
"embeddings",
" rag",
" retrieval",
" vectara"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "121521f7522434246146eed9a9b0b20976ff3bac52f7267a380d896b732136dd",
"md5": "5bcdf35f2e3653f8310f4398ee39b766",
"sha256": "fe45770c6054297fec6c538f46fdaa20e7887e0ceb26dc326c57923a540d929f"
},
"downloads": -1,
"filename": "llama_index_packs_vectara_rag-0.5.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5bcdf35f2e3653f8310f4398ee39b766",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 4570,
"upload_time": "2025-07-31T02:23:40",
"upload_time_iso_8601": "2025-07-31T02:23:40.327425Z",
"url": "https://files.pythonhosted.org/packages/12/15/21f7522434246146eed9a9b0b20976ff3bac52f7267a380d896b732136dd/llama_index_packs_vectara_rag-0.5.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "7abcf0df151021c5f781ef6e48231f9c2785a41df78ce47f9c812a36b9e427dc",
"md5": "6170352e9afbb98a21115138b2b246e2",
"sha256": "7770dbe86a83c1ecc5ffb72213a12996d9a44f0252a22715272ba65bd27698aa"
},
"downloads": -1,
"filename": "llama_index_packs_vectara_rag-0.5.0.tar.gz",
"has_sig": false,
"md5_digest": "6170352e9afbb98a21115138b2b246e2",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 5013,
"upload_time": "2025-07-31T02:23:41",
"upload_time_iso_8601": "2025-07-31T02:23:41.472619Z",
"url": "https://files.pythonhosted.org/packages/7a/bc/f0df151021c5f781ef6e48231f9c2785a41df78ce47f9c812a36b9e427dc/llama_index_packs_vectara_rag-0.5.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-31 02:23:41",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-packs-vectara-rag"
}
JSON