cli

Name: cli
Author: pinecone-io

23stars1forks

How to install cli?

pinecone-io/gemini-cli-extension/cli

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

Installs into the current project.

Summary

Guide for using the Pinecone CLI (pc) to manage Pinecone resources from the terminal. The CLI supports ALL index types (standard, integrated, sparse) and all vector operations — unlike the MCP which only supports integrated indexes. Use for batch operations, vector management, ba

Files · 1

View on GitHub

SKILL.md

1	# Pinecone CLI (`pc`)
2
3	Manage Pinecone from the terminal. The CLI is especially valuable for vector operations across all index types — something the MCP currently can't do.
4
5	## CLI vs MCP
6
7	\| \| CLI \| MCP \|
8	\|---\|---\|---\|
9	\| Index types \| All (standard, integrated, sparse) \| Integrated only \|
10	\| Vector ops (upsert, query, fetch, update, delete) \| ✅ \| ❌ \|
11	\| Text search on integrated indexes \| ✅ \| ✅ \|
12	\| Backups, namespaces, org/project mgmt \| ✅ \| ❌ \|
13	\| CI/CD / scripting \| ✅ \| ❌ \|
14
15	---
16
17	## Setup
18
19	### Install (macOS)
20	```bash
21	brew tap pinecone-io/tap
22	brew install pinecone-io/tap/pinecone
23	```
24
25	Other platforms (Linux, Windows) — download from [GitHub Releases](https://github.com/pinecone-io/cli/releases).
26
27	### Authenticate
28
29	```bash
30	# Interactive (recommended for local dev)
31	pc login
32	pc target -o "my-org" -p "my-project"
33
34	# Service account (recommended for CI/CD)
35	pc auth configure --client-id "$PINECONE_CLIENT_ID" --client-secret "$PINECONE_CLIENT_SECRET"
36
37	# API key (quick testing)
38	pc config set-api-key $PINECONE_API_KEY
39	```
40
41	Check status: `pc auth status` · `pc target --show`
42
43	> Note for agent sessions: If you need to run `pc login` inside an agent loop, the browser auth link may not surface correctly. It's best to authenticate before starting an agent session. Run `pc login` in your terminal directly, then invoke the agent once you're authenticated.
44
45	### Authenticating the CLI does not set `PINECONE_API_KEY`
46
47	`pc login` authenticates the CLI tool itself — it does not set `PINECONE_API_KEY` in your environment. Python scripts, Node.js SDKs, and other tools that use the Pinecone SDK need `PINECONE_API_KEY` set separately.
48
49	Use the CLI to create a key and export it in one step:
50
51	```bash
52	KEY=$(pc api-key create --name agent-sdk-key --json \| jq -r '.value')
53	export PINECONE_API_KEY="$KEY"
54	```
55
56	Without `jq`: run `pc api-key create --name agent-sdk-key --json` and copy the `"value"` field manually.
57
58	---
59
60	## Common Commands
61
62	\| Task \| Command \|
63	\|---\|---\|
64	\| List indexes \| `pc index list` \|
65	\| Create serverless index \| `pc index create -n my-index -d 1536 -m cosine -c aws -r us-east-1` \|
66	\| Index stats \| `pc index stats -n my-index` \|
67	\| Upload vectors from file \| `pc index vector upsert -n my-index --file ./vectors.json` \|
68	\| Query by vector \| `pc index vector query -n my-index --vector '[0.1, ...]' -k 10 --include-metadata` \|
69	\| Query by vector ID \| `pc index vector query -n my-index --id "doc-123" -k 10` \|
70	\| Fetch vectors by ID \| `pc index vector fetch -n my-index --ids '["vec1","vec2"]'` \|
71	\| List vector IDs \| `pc index vector list -n my-index` \|
72	\| Delete vectors by filter \| `pc index vector delete -n my-index --filter '{"genre":"classical"}'` \|
73	\| List namespaces \| `pc index namespace list -n my-index` \|
74	\| Create backup \| `pc backup create -i my-index -n "my-backup"` \|
75	\| JSON output (for scripting) \| Add `-j` to any command \|
76
77	---
78
79	## Interesting Things You Can Do
80
81	### Query with custom vectors (not just text)
82	Unlike the MCP, the CLI lets you query any index with raw vector values — useful when you generate embeddings externally (OpenAI, HuggingFace, etc.):
83	```bash
84	pc index vector query -n my-index \
85	--vector '[0.1, 0.2, ..., 0.9]' \
86	--filter '{"source":{"$eq":"docs"}}' \
87	-k 20 --include-metadata
88	```
89
90	### Pipe embeddings directly into queries
91	```bash
92	jq -c '.embedding' doc.json \| pc index vector query -n my-index --vector - -k 10
93	```
94
95	### Bulk metadata update with preview
96	```bash
97	# Preview first
98	pc index vector update -n my-index \
99	--filter '{"env":{"$eq":"staging"}}' \
100	--metadata '{"env":"production"}' \
101	--dry-run
102
103	# Apply
104	pc index vector update -n my-index \
105	--filter '{"env":{"$eq":"staging"}}' \
106	--metadata '{"env":"production"}'
107	```
108
109	### Backup and restore
110	```bash
111	# Snapshot before a migration
112	pc backup create -i my-index -n "pre-migration"
113
114	# Restore to a new index if something goes wrong
115	pc backup restore -i <backup-uuid> -n my-index-restored
116	```
117
118	### Automate in CI/CD
119	```bash
120	export PINECONE_CLIENT_ID="..."
121	export PINECONE_CLIENT_SECRET="..."
122	pc auth configure --client-id "$PINECONE_CLIENT_ID" --client-secret "$PINECONE_CLIENT_SECRET"
123	pc index vector upsert -n my-index --file ./vectors.jsonl --batch-size 1000
124	```
125
126	### Script against JSON output
127	```bash
128	# Get all index names as a list
129	pc index list -j \| jq -r '.[] \| .name'
130
131	# Check if an index exists before creating
132	if ! pc index describe -n my-index -j 2>/dev/null \| jq -e '.name' > /dev/null; then
133	pc index create -n my-index -d 1536 -m cosine -c aws -r us-east-1
134	fi
135	```
136
137	---
138
139	## Reference Files
140
141	- [Full command reference](references/command-reference.md) — all

People who liked this also viewed

6 picks

Type

cli

23stars1forks

View on GitHub

How to install cli?

pinecone-io/gemini-cli-extension/cli

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Pinecone CLI (`pc`)
2
3	Manage Pinecone from the terminal. The CLI is especially valuable for vector operations across all index types — something the MCP currently can't do.
4
5	## CLI vs MCP
6
7	\| \| CLI \| MCP \|
8	\|---\|---\|---\|
9	\| Index types \| All (standard, integrated, sparse) \| Integrated only \|
10	\| Vector ops (upsert, query, fetch, update, delete) \| ✅ \| ❌ \|
11	\| Text search on integrated indexes \| ✅ \| ✅ \|
12	\| Backups, namespaces, org/project mgmt \| ✅ \| ❌ \|
13	\| CI/CD / scripting \| ✅ \| ❌ \|
14
15	---
16
17	## Setup
18
19	### Install (macOS)
20	```bash
21	brew tap pinecone-io/tap
22	brew install pinecone-io/tap/pinecone
23	```
24
25	Other platforms (Linux, Windows) — download from [GitHub Releases](https://github.com/pinecone-io/cli/releases).
26
27	### Authenticate
28
29	```bash
30	# Interactive (recommended for local dev)
31	pc login
32	pc target -o "my-org" -p "my-project"
33
34	# Service account (recommended for CI/CD)
35	pc auth configure --client-id "$PINECONE_CLIENT_ID" --client-secret "$PINECONE_CLIENT_SECRET"
36
37	# API key (quick testing)
38	pc config set-api-key $PINECONE_API_KEY
39	```
40
41	Check status: `pc auth status` · `pc target --show`
42
43	> Note for agent sessions: If you need to run `pc login` inside an agent loop, the browser auth link may not surface correctly. It's best to authenticate before starting an agent session. Run `pc login` in your terminal directly, then invoke the agent once you're authenticated.
44
45	### Authenticating the CLI does not set `PINECONE_API_KEY`
46
47	`pc login` authenticates the CLI tool itself — it does not set `PINECONE_API_KEY` in your environment. Python scripts, Node.js SDKs, and other tools that use the Pinecone SDK need `PINECONE_API_KEY` set separately.
48
49	Use the CLI to create a key and export it in one step:
50
51	```bash
52	KEY=$(pc api-key create --name agent-sdk-key --json \| jq -r '.value')
53	export PINECONE_API_KEY="$KEY"
54	```
55
56	Without `jq`: run `pc api-key create --name agent-sdk-key --json` and copy the `"value"` field manually.
57
58	---
59
60	## Common Commands
61
62	\| Task \| Command \|
63	\|---\|---\|
64	\| List indexes \| `pc index list` \|
65	\| Create serverless index \| `pc index create -n my-index -d 1536 -m cosine -c aws -r us-east-1` \|
66	\| Index stats \| `pc index stats -n my-index` \|
67	\| Upload vectors from file \| `pc index vector upsert -n my-index --file ./vectors.json` \|
68	\| Query by vector \| `pc index vector query -n my-index --vector '[0.1, ...]' -k 10 --include-metadata` \|
69	\| Query by vector ID \| `pc index vector query -n my-index --id "doc-123" -k 10` \|
70	\| Fetch vectors by ID \| `pc index vector fetch -n my-index --ids '["vec1","vec2"]'` \|
71	\| List vector IDs \| `pc index vector list -n my-index` \|
72	\| Delete vectors by filter \| `pc index vector delete -n my-index --filter '{"genre":"classical"}'` \|
73	\| List namespaces \| `pc index namespace list -n my-index` \|
74	\| Create backup \| `pc backup create -i my-index -n "my-backup"` \|
75	\| JSON output (for scripting) \| Add `-j` to any command \|
76
77	---
78
79	## Interesting Things You Can Do
80
81	### Query with custom vectors (not just text)
82	Unlike the MCP, the CLI lets you query any index with raw vector values — useful when you generate embeddings externally (OpenAI, HuggingFace, etc.):
83	```bash
84	pc index vector query -n my-index \
85	--vector '[0.1, 0.2, ..., 0.9]' \
86	--filter '{"source":{"$eq":"docs"}}' \
87	-k 20 --include-metadata
88	```
89
90	### Pipe embeddings directly into queries
91	```bash
92	jq -c '.embedding' doc.json \| pc index vector query -n my-index --vector - -k 10
93	```
94
95	### Bulk metadata update with preview
96	```bash
97	# Preview first
98	pc index vector update -n my-index \
99	--filter '{"env":{"$eq":"staging"}}' \
100	--metadata '{"env":"production"}' \
101	--dry-run
102
103	# Apply
104	pc index vector update -n my-index \
105	--filter '{"env":{"$eq":"staging"}}' \
106	--metadata '{"env":"production"}'
107	```
108
109	### Backup and restore
110	```bash
111	# Snapshot before a migration
112	pc backup create -i my-index -n "pre-migration"
113
114	# Restore to a new index if something goes wrong
115	pc backup restore -i <backup-uuid> -n my-index-restored
116	```
117
118	### Automate in CI/CD
119	```bash
120	export PINECONE_CLIENT_ID="..."
121	export PINECONE_CLIENT_SECRET="..."
122	pc auth configure --client-id "$PINECONE_CLIENT_ID" --client-secret "$PINECONE_CLIENT_SECRET"
123	pc index vector upsert -n my-index --file ./vectors.jsonl --batch-size 1000
124	```
125
126	### Script against JSON output
127	```bash
128	# Get all index names as a list
129	pc index list -j \| jq -r '.[] \| .name'
130
131	# Check if an index exists before creating
132	if ! pc index describe -n my-index -j 2>/dev/null \| jq -e '.name' > /dev/null; then
133	pc index create -n my-index -d 1536 -m cosine -c aws -r us-east-1
134	fi
135	```
136
137	---
138
139	## Reference Files
140
141	- [Full command reference](references/command-reference.md) — all

People who liked this also viewed

6 picks

Type