| Name | llama-index-tools-vectara-query JSON |
| Version |
0.2.0
JSON |
| download |
| home_page | None |
| Summary | llama-index tools vectara query integration |
| upload_time | 2024-11-18 00:57:32 |
| maintainer | None |
| docs_url | None |
| author | David Oplatka |
| requires_python | <4.0,>=3.9 |
| license | MIT |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
## Vectara Query Tool
This tool connects to a Vectara corpus and allows agents to make semantic search or retrieval augmented generation (RAG) queries.
## Usage
This tool has a more extensive example usage documented in a Jupyter notebok [here](https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/tools/llama-index-tools-vectara-query/examples/vectara_query.ipynb)
To use this tool, you'll need the following information in your environment:
- `VECTARA_CUSTOMER_ID`: The customer id for your Vectara account. If you don't have an account, you can create one [here](https://vectara.com/integrations/llamaindex).
- `VECTARA_CORPUS_ID`: The corpus id for the Vectara corpus that you want your tool to search for information. If you need help creating a corpus with your data, follow this [Quick Start](https://docs.vectara.com/docs/quickstart) guide.
- `VECTARA_API_KEY`: An API key that can perform queries on this corpus.
Here's an example usage of the VectaraQueryToolSpec.
```python
from llama_index.tools.vectara_query import VectaraQueryToolSpec
from llama_index.agent.openai import OpenAIAgent
# Connecting to a Vectara corpus about Electric Vehicles
tool_spec = VectaraQueryToolSpec()
agent = OpenAIAgent.from_tools(tool_spec.to_tool_list())
agent.chat("What are the different types of electric vehicles?")
```
The available tools are:
`semantic_search`: A tool that accepts a query and uses semantic search to obtain the top search results.
`rag_query`: A tool that accepts a query and uses RAG to obtain a generative response grounded in the search results.
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-tools-vectara-query",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": null,
"author": "David Oplatka",
"author_email": "david.oplatka@vectara.com",
"download_url": "https://files.pythonhosted.org/packages/e2/4a/20098d87c1d177e568a3ce2d707f57317b3538927cb25a4963b67d33c7d3/llama_index_tools_vectara_query-0.2.0.tar.gz",
"platform": null,
"description": "## Vectara Query Tool\n\nThis tool connects to a Vectara corpus and allows agents to make semantic search or retrieval augmented generation (RAG) queries.\n\n## Usage\n\nThis tool has a more extensive example usage documented in a Jupyter notebok [here](https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/tools/llama-index-tools-vectara-query/examples/vectara_query.ipynb)\n\nTo use this tool, you'll need the following information in your environment:\n\n- `VECTARA_CUSTOMER_ID`: The customer id for your Vectara account. If you don't have an account, you can create one [here](https://vectara.com/integrations/llamaindex).\n- `VECTARA_CORPUS_ID`: The corpus id for the Vectara corpus that you want your tool to search for information. If you need help creating a corpus with your data, follow this [Quick Start](https://docs.vectara.com/docs/quickstart) guide.\n- `VECTARA_API_KEY`: An API key that can perform queries on this corpus.\n\nHere's an example usage of the VectaraQueryToolSpec.\n\n```python\nfrom llama_index.tools.vectara_query import VectaraQueryToolSpec\nfrom llama_index.agent.openai import OpenAIAgent\n\n# Connecting to a Vectara corpus about Electric Vehicles\ntool_spec = VectaraQueryToolSpec()\n\nagent = OpenAIAgent.from_tools(tool_spec.to_tool_list())\n\nagent.chat(\"What are the different types of electric vehicles?\")\n```\n\nThe available tools are:\n\n`semantic_search`: A tool that accepts a query and uses semantic search to obtain the top search results.\n\n`rag_query`: A tool that accepts a query and uses RAG to obtain a generative response grounded in the search results.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index tools vectara query integration",
"version": "0.2.0",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "e7c305ce3759bbc4e970536ae148d977bcbaed38985312ef981e12685e800a11",
"md5": "d0b0349709c0e7457a022aabd4c44345",
"sha256": "a930c4e158e42e1b1137af71f391495046893e0464e0242f4872b68be4e9ce89"
},
"downloads": -1,
"filename": "llama_index_tools_vectara_query-0.2.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "d0b0349709c0e7457a022aabd4c44345",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 4482,
"upload_time": "2024-11-18T00:57:31",
"upload_time_iso_8601": "2024-11-18T00:57:31.445222Z",
"url": "https://files.pythonhosted.org/packages/e7/c3/05ce3759bbc4e970536ae148d977bcbaed38985312ef981e12685e800a11/llama_index_tools_vectara_query-0.2.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "e24a20098d87c1d177e568a3ce2d707f57317b3538927cb25a4963b67d33c7d3",
"md5": "00463a5eb524c1bdff7e6e812baab041",
"sha256": "7591d4c1065202f0b1a636c9dbb079d2b95593c76b795be32a7f236310058cdf"
},
"downloads": -1,
"filename": "llama_index_tools_vectara_query-0.2.0.tar.gz",
"has_sig": false,
"md5_digest": "00463a5eb524c1bdff7e6e812baab041",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 4145,
"upload_time": "2024-11-18T00:57:32",
"upload_time_iso_8601": "2024-11-18T00:57:32.990345Z",
"url": "https://files.pythonhosted.org/packages/e2/4a/20098d87c1d177e568a3ce2d707f57317b3538927cb25a4963b67d33c7d3/llama_index_tools_vectara_query-0.2.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-11-18 00:57:32",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-tools-vectara-query"
}
