doc get to vector enrich-doc help example does not work

[ingenthr]

There is more than one issue here I think, but I'll focus on the vector enrich-doc help example. If I run that and specify the model, I get an error. For my document, this matches the help:

> doc get foo | select content | vector enrich-doc foo --model text-embedding-3-small
Embedding batch 1/1 
Error:   × Could not locate 'id' field in docs, if not called 'id' specify using --id-column

I hit several other errors though:

• trying to pipe doc get straight into vector enrich-doc gives me "can't convert string to record"
• selecting content gives a complaint about wanting ID (on a vector enrich?), but doesn't work even if it has an id as shown below where I select both content and id. The error isn't very clear "Error: × Could not locate 'id' field in docs, if not called 'id' specify using --id-column"

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> vector enrich-doc -h
Enriches given JSON with embeddings of selected field

Usage:
  > vector enrich-doc {flags} <field> 

Flags:
  -h, --help - Display the help message for this command
  --model <String> - the model to generate the embeddings with
  --dimension <Int> - dimension of the resulting embeddings
  --maxTokens <Int> - the token per minute limit for the provider/model
  --id-column <String> - the name of the id column if used with an input stream
  --vectorField <String> - the name of the field into which the embedding is written, defaults to fieldVector

Parameters:
  field <string>: the field from which the vector is generated

Examples:
  Open local json doc and enrich the field named 'description'
  > open ./local.json | vector enrich-doc description --model amazon.titan-embed-text-v2:0

  Fetch a single doc with id '12345' and enrich the field named 'description'
  > doc get 12345 | select content | vector enrich-doc description --model models/text-embedding-004

  Fetch and enrich all landmark documents from travel sample and upload the results to couchabase
  > query  'SELECT * FROM `travel-sample` WHERE type = "landmark"' | select content | vector enrich-doc content --model amazon.titan-embed-text-v1 | doc upsert

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | vector enrich-doc
Error: nu::parser::missing_positional

  × Missing required positional argument.
   ╭─[entry #115:1:32]
 1 │ doc get foo | vector enrich-doc
   ╰────
  help: Usage: vector enrich-doc {flags} <field> . Use `--help` for more information.

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | vector enrich-doc description
Error:   × no embed model provided
   ╭─[entry #116:1:15]
 1 │ doc get foo | vector enrich-doc description
   ·               ────────┬────────
   ·                       ╰── 
   ╰────
  help: supply the embed_model in the config file or using the --model flag

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | vector enrich-doc description --model models/text-embedding-004
Error:   × Could not parse input from query

Error: nu::shell::cant_convert

  × Can't convert to record.
   ╭─[entry #117:1:1]
 1 │ doc get foo | vector enrich-doc description --model models/text-embedding-004
   · ───┬───
   ·    ╰── can't convert string to record
   ╰────

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content | vector enrich-doc description --model models/text-embedding-004
Error:   × The field 'description' must be present in input record

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content | vector enrich-doc foo --model models/text-embedding-004
Embedding batch 1/1 
Error:   × invalid model ID

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> cb-env
╭──────────────┬───────────────╮
│ username     │ Administrator │
│ display_name │ Administrator │
│ cluster      │ dino          │
│ bucket       │ jiraexp       │
│ scope        │ issues        │
│ collection   │ users         │
│ cluster_type │ other         │
│ llm          │ ingOpenAI     │
╰──────────────┴───────────────╯
👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> text-embedding-3-small
👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content | vector enrich-doc foo --model models/text-embedding-3-small
Embedding batch 1/1 
Error:   × invalid model ID

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content | vector enrich-doc foo --model models/text-embedding-3-large
Embedding batch 1/1 
Error:   × invalid model ID

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content | vector enrich-doc foo --model models/text-embedding-ada-002
Embedding batch 1/1 
Error:   × invalid model ID

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content | vector enrich-doc foo --model text-embedding-3-small
Embedding batch 1/1 
Error:   × Could not locate 'id' field in docs, if not called 'id' specify using --id-column

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | vector enrich-doc foo --model text-embedding-3-small
Error:   × Could not parse input from query

Error: nu::shell::cant_convert

  × Can't convert to record.
   ╭─[entry #126:1:1]
 1 │ doc get foo | vector enrich-doc foo --model text-embedding-3-small
   · ───┬───
   ·    ╰── can't convert string to record
   ╰────

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content | vector enrich-doc foo --model text-embedding-3-small
Embedding batch 1/1 
Error:   × Could not locate 'id' field in docs, if not called 'id' specify using --id-column

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content | vector enrich-text foo --model text-embedding-3-small
Error:   × Could not parse list of files

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> vector enrich-doc -h
Enriches given JSON with embeddings of selected field

Usage:
  > vector enrich-doc {flags} <field> 

Flags:
  -h, --help - Display the help message for this command
  --model <String> - the model to generate the embeddings with
  --dimension <Int> - dimension of the resulting embeddings
  --maxTokens <Int> - the token per minute limit for the provider/model
  --id-column <String> - the name of the id column if used with an input stream
  --vectorField <String> - the name of the field into which the embedding is written, defaults to fieldVector

Parameters:
  field <string>: the field from which the vector is generated

Examples:
  Open local json doc and enrich the field named 'description'
  > open ./local.json | vector enrich-doc description --model amazon.titan-embed-text-v2:0

  Fetch a single doc with id '12345' and enrich the field named 'description'
  > doc get 12345 | select content | vector enrich-doc description --model models/text-embedding-004

  Fetch and enrich all landmark documents from travel sample and upload the results to couchabase
  > query  'SELECT * FROM `travel-sample` WHERE type = "landmark"' | select content | vector enrich-doc content --model amazon.titan-embed-text-v1 | doc upsert

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content id | vector enrich-doc foo --model text-embedding-3-small
Embedding batch 1/1 
Error:   × Could not locate 'id' field in docs, if not called 'id' specify using --id-column

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo
╭───┬─────┬───────────────┬─────────────────────┬───────┬─────────╮
│ # │ id  │    content    │         cas         │ error │ cluster │
├───┼─────┼───────────────┼─────────────────────┼───────┼─────────┤
│ 0 │ foo │ ╭─────┬─────╮ │ 1723616346915012608 │       │ dino    │
│   │     │ │ foo │ bar │ │                     │       │         │
│   │     │ ╰─────┴─────╯ │                     │       │         │
╰───┴─────┴───────────────┴─────────────────────┴───────┴─────────╯
👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content id 
╭───┬───────────────┬─────╮
│ # │    content    │ id  │
├───┼───────────────┼─────┤
│ 0 │ ╭─────┬─────╮ │ foo │
│   │ │ foo │ bar │ │     │
│   │ ╰─────┴─────╯ │     │
╰───┴───────────────┴─────╯
👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content id | vector enrich-doc 
Error: nu::parser::missing_positional

  × Missing required positional argument.
   ╭─[entry #133:1:52]
 1 │ doc get foo | select content id | vector enrich-doc 
   ·                                                    ▲
   ·                                                    ╰── missing field
   ╰────
  help: Usage: vector enrich-doc {flags} <field> . Use `--help` for more information.

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content id | vector enrich-doc foo
Error:   × no embed model provided
   ╭─[entry #134:1:35]
 1 │ doc get foo | select content id | vector enrich-doc foo
   ·                                   ────────┬────────
   ·                                           ╰── 
   ╰────
  help: supply the embed_model in the config file or using the --model flag

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select content id | vector enrich-doc foo --model text-embedding-3-small
Embedding batch 1/1 
Error:   × Could not locate 'id' field in docs, if not called 'id' specify using --id-column

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | select id content | vector enrich-doc foo --model text-embedding-3-small
Error:   × Could not parse input from query

Error: nu::shell::cant_convert

  × Can't convert to record.
   ╭─[entry #136:1:1]
 1 │ doc get foo | select id content | vector enrich-doc foo --model text-embedding-3-small
   · ───┬───
   ·    ╰── can't convert string to record
   ╰────

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | range 0..0 | vector enrich-doc foo --model text-embedding-3-small
Error:   × Could not parse input from query

Error: nu::shell::cant_convert

  × Can't convert to record.
   ╭─[entry #137:1:1]
 1 │ doc get foo | range 0..0 | vector enrich-doc foo --model text-embedding-3-small
   · ───┬───
   ·    ╰── can't convert string to record
   ╰────

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | to json | vector enrich-doc foo --model text-embedding-3-small
Error:   × Piped input must a json doc or a list of json docs

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users
> doc get foo | vector enrich-doc foo --model text-embedding-3-small
Error:   × Could not parse input from query

Error: nu::shell::cant_convert

  × Can't convert to record.
   ╭─[entry #139:1:1]
 1 │ doc get foo | vector enrich-doc foo --model text-embedding-3-small
   · ───┬───
   ·    ╰── can't convert string to record
   ╰────

👤 Administrator 🏠 dino in 🗄 jiraexp.issues.users

[vishaldhiman22]

My observation has been similar as well. I think "vector enrich-doc" should be flexible to support 2 types of input:

Type 1: Support flattened list as input. See example below:

Type 2: Support Key, Value as input. See example below: