query

Name: query
Author: pinecone-io

23stars1forks

How to install query?

pinecone-io/gemini-cli-extension/query

$npx -y skills add pinecone-io/gemini-cli-extension --skill query

Installs into the current project.

Summary

Query integrated indexes using text with Pinecone MCP. IMPORTANT - This skill ONLY works with integrated indexes (indexes with built-in Pinecone embedding models like multilingual-e5-large). For standard indexes or advanced vector operations, use the CLI skill instead. Requires P

Files · 1

View on GitHub

SKILL.md

1	# Pinecone Query Skill
2
3	Search for records in Pinecone integrated indexes using natural language text queries via the Pinecone MCP server.
4
5	## What is this skill for?
6
7	This skill provides a simple way to query integrated indexes (indexes with built-in Pinecone embedding models) using text queries. The MCP server automatically converts your text into embeddings and searches the index.
8
9	### Prerequisites
10
11	Required:
12	1. ✅ Pinecone MCP server must be configured - Check if MCP tools are available
13	2. ✅ PINECONE_API_KEY environment variable must be set - Get a free API key at https://app.pinecone.io/?sessionType=signup
14	3. ✅ Index must be an integrated index - Uses Pinecone embedding models (e.g., multilingual-e5-large, llama-text-embed-v2, pinecone-sparse-english-v0)
15
16	### When NOT to use this skill
17
18	Use the CLI skill instead if:
19	- ❌ Your index is a standard index (no integrated embedding model)
20	- ❌ You need to query with custom vector values (not text)
21	- ❌ You need advanced vector operations (fetch by ID, list vectors, bulk operations)
22	- ❌ Your index uses third-party embedding models (OpenAI, HuggingFace, Cohere)
23
24	MCP Limitation: The Pinecone MCP currently only supports integrated indexes. For all other use cases, use the Pinecone CLI skill.
25
26	## How it works
27
28	Utilize Pinecone MCP's `search-records` tool to search for records within a specified Pinecone integrated index using a text query.
29
30	## Workflow
31
32	IMPORTANT: Before proceeding, verify the Pinecone MCP tools are available. If MCP tools are not accessible:
33	- Inform the user that the Pinecone MCP server needs to be configured
34	- Check if `PINECONE_API_KEY` environment variable is set
35	- Direct them to the MCP setup documentation or the `help` skill
36
37	1. Parse the user's input for:
38	- `query` (required): The text to search for.
39	- `index` (required): The name of the Pinecone index to search.
40	- `namespace` (optional): The namespace within the index.
41	- `reranker` (optional): The reranking model to use for improved relevance.
42
43	2. If the user omits required arguments:
44	- If only the index name is provided, use the `describe-index` tool to retrieve available namespaces and ask the user to choose.
45	- If only a query is provided, use `list-indexes` to get available indexes, ask the user to pick one, then use `describe-index` for namespaces if needed.
46
47	3. Call the `search-records` tool with the gathered arguments to perform the search.
48
49	4. Format and display the returned results in a clear, readable table including field highlights (such as ID, score, and relevant metadata).
50
51	---
52
53	## Troubleshooting
54
55	`PINECONE_API_KEY` is required. Get a free key at https://app.pinecone.io/?sessionType=signup
56
57	If you get an access error, the key is likely missing. Ask the user to set it and restart their IDE or agent session:
58	- Terminal: `export PINECONE_API_KEY="your-key"`
59	- IDE without shell inheritance: add `PINECONE_API_KEY=your-key` to a `.env` file
60
61	IMPORTANT At the moment, the query action can only be used with integrated indexes, which use hosted Pinecone embedding models to embed and search for data.
62	If a user attempts to query an index that uses a third party API model such as OpenAI, or HuggingFace embedding models, remind them that this capability is not available yet
63	with the Pinecone MCP server.
64
65	- If required arguments are missing, prompt the user to supply them, using Pinecone MCP tools as needed (e.g., `list-indexes`, `describe-index`).
66	- Guide the user interactively through argument selection until the search can be completed.
67	- If an invalid value is provided for any argument (e.g., nonexistent index or namespace), surface the error and suggest valid options.
68
69	## Tools Reference
70
71	- `search-records`: Search records in a given index with optional metadata filtering and reranking.
72	- `list-indexes`: List all available Pinecone indexes.
73	- `describe-index`: Get index configuration and namespaces.
74	- `describe-index-stats`: Get stats including record counts and namespaces.
75	- `rerank-documents`: Rerank returned documents using a specified reranking model.
76	- Ask the user interactively to clarify missing information when needed.
77
78	---

People who liked this also viewed

6 picks

Type

query

23stars1forks

View on GitHub

How to install query?

pinecone-io/gemini-cli-extension/query

$npx -y skills add pinecone-io/gemini-cli-extension --skill query

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Pinecone Query Skill
2
3	Search for records in Pinecone integrated indexes using natural language text queries via the Pinecone MCP server.
4
5	## What is this skill for?
6
7	This skill provides a simple way to query integrated indexes (indexes with built-in Pinecone embedding models) using text queries. The MCP server automatically converts your text into embeddings and searches the index.
8
9	### Prerequisites
10
11	Required:
12	1. ✅ Pinecone MCP server must be configured - Check if MCP tools are available
13	2. ✅ PINECONE_API_KEY environment variable must be set - Get a free API key at https://app.pinecone.io/?sessionType=signup
14	3. ✅ Index must be an integrated index - Uses Pinecone embedding models (e.g., multilingual-e5-large, llama-text-embed-v2, pinecone-sparse-english-v0)
15
16	### When NOT to use this skill
17
18	Use the CLI skill instead if:
19	- ❌ Your index is a standard index (no integrated embedding model)
20	- ❌ You need to query with custom vector values (not text)
21	- ❌ You need advanced vector operations (fetch by ID, list vectors, bulk operations)
22	- ❌ Your index uses third-party embedding models (OpenAI, HuggingFace, Cohere)
23
24	MCP Limitation: The Pinecone MCP currently only supports integrated indexes. For all other use cases, use the Pinecone CLI skill.
25
26	## How it works
27
28	Utilize Pinecone MCP's `search-records` tool to search for records within a specified Pinecone integrated index using a text query.
29
30	## Workflow
31
32	IMPORTANT: Before proceeding, verify the Pinecone MCP tools are available. If MCP tools are not accessible:
33	- Inform the user that the Pinecone MCP server needs to be configured
34	- Check if `PINECONE_API_KEY` environment variable is set
35	- Direct them to the MCP setup documentation or the `help` skill
36
37	1. Parse the user's input for:
38	- `query` (required): The text to search for.
39	- `index` (required): The name of the Pinecone index to search.
40	- `namespace` (optional): The namespace within the index.
41	- `reranker` (optional): The reranking model to use for improved relevance.
42
43	2. If the user omits required arguments:
44	- If only the index name is provided, use the `describe-index` tool to retrieve available namespaces and ask the user to choose.
45	- If only a query is provided, use `list-indexes` to get available indexes, ask the user to pick one, then use `describe-index` for namespaces if needed.
46
47	3. Call the `search-records` tool with the gathered arguments to perform the search.
48
49	4. Format and display the returned results in a clear, readable table including field highlights (such as ID, score, and relevant metadata).
50
51	---
52
53	## Troubleshooting
54
55	`PINECONE_API_KEY` is required. Get a free key at https://app.pinecone.io/?sessionType=signup
56
57	If you get an access error, the key is likely missing. Ask the user to set it and restart their IDE or agent session:
58	- Terminal: `export PINECONE_API_KEY="your-key"`
59	- IDE without shell inheritance: add `PINECONE_API_KEY=your-key` to a `.env` file
60
61	IMPORTANT At the moment, the query action can only be used with integrated indexes, which use hosted Pinecone embedding models to embed and search for data.
62	If a user attempts to query an index that uses a third party API model such as OpenAI, or HuggingFace embedding models, remind them that this capability is not available yet
63	with the Pinecone MCP server.
64
65	- If required arguments are missing, prompt the user to supply them, using Pinecone MCP tools as needed (e.g., `list-indexes`, `describe-index`).
66	- Guide the user interactively through argument selection until the search can be completed.
67	- If an invalid value is provided for any argument (e.g., nonexistent index or namespace), surface the error and suggest valid options.
68
69	## Tools Reference
70
71	- `search-records`: Search records in a given index with optional metadata filtering and reranking.
72	- `list-indexes`: List all available Pinecone indexes.
73	- `describe-index`: Get index configuration and namespaces.
74	- `describe-index-stats`: Get stats including record counts and namespaces.
75	- `rerank-documents`: Rerank returned documents using a specified reranking model.
76	- Ask the user interactively to clarify missing information when needed.
77
78	---

People who liked this also viewed

6 picks

Type