Integrate an Agent with the Agent Catalog

agentc add 
Record Kind (python_function, sqlpp_query, semantic_search, http_request, prompt): python_function
Now building a new tool / prompt file. The output will be saved to: $PROJECT_PATH
Type: python_function

# Your function name must be written in snake case. 
Name: my_python_function 

Description: My first Python tool for my AI agent
Python (function) tool written to: $PROJECT_PATH\my_python_function.py

# The following file has been automatically generated by agentc at 11:05AM on October 31, 2024.

from agentc import tool
from pydantic import BaseModel


# Although Python uses duck-typing, the specification of models greatly improves the response quality of LLMs.
# It is highly recommended that all tools specify the models of their bound functions using Pydantic or dataclasses.
# class SalesModel(BaseModel):
#     input_sources: list[str]
#     sales_formula: str


# Only functions decorated with "tool" will be indexed.
# All other functions / module members will be ignored by the indexer.
tool
def my_python_function(<<< Replace me with your input type! >>>) -> <<< Replace me with your output type! >>>:
    """My first Python tool for my AI agent"""

    <<< Replace me with your Python code! >>>

agentc add
Record Kind (python_function, sqlpp_query, semantic_search, http_request, prompt): sqlpp_query
Now building a new tool / prompt file. The output will be saved to: $PROJECT_PATH
Type: sqlpp_query

# Your sqlpp_query name must be written in snake case.
Name: my_sqlpp_query

Description: A query to find a list of direct routes between two airports, using source_airport and destination_airport.
SQL++ query tool written to: $PROJECT_PATH\my_sqlpp_query.sqlpp

--
/*
# The name of the query must be a valid Python identifier - the name cannot include spaces.
name: my_sqlpp_query

# The description will be used in the docstring for this query's generated Python function.
description: >
    A query to find a list of direct routes between two airports, using source_airport and destination_airport.

# The inputs used to resolve the named parameters in the SQL++ query below.
# Inputs are described using a JSON object that follows the JSON schema standard.
# This field is mandatory, and will be used to build a Pydantic model.
# See https://json-schema.org/learn/getting-started-step-by-step for more info.
input: >
   <<< Replace me with your input type! >>>

# The outputs used describe the structure of the SQL++ query result.
# Outputs are described using a JSON object that follows the JSON schema standard.
# This field is mandatory, and will be used to build a Pydantic model.
# We recommend using the 'INFER' command to build a JSON schema from your query results.
# See https://docs.couchbase.com/server/current/n1ql/n1ql-language-reference/infer.html.
# In the future, this field will be optional (we will INFER the query automatically for you).
output: >
   <<< Replace me with your output type! >>>

# As a supplement to the tool similarity search, users can optionally specify search annotations.
# The values of these annotations MUST be strings (e.g., not 'true', but '"true"').
# This field is optional, and does not have to be present.
# annotations:
#   gdpr_2016_compliant: "false"
#   ccpa_2019_compliant: "true"

# The "secrets" field defines search keys that will be used to query a "secrets" manager.
# Note that these values are NOT the secrets themselves, rather they are used to lookup secrets.
secrets:

    # All Couchbase tools (e.g., semantic search, SQL++) must specify conn_string, username, and password.
    - couchbase:
        conn_string: CB_CONN_STRING
        username: CB_USERNAME
        password: CB_PASSWORD
*/
<<< Replace me with your SQL++ query! >>>

agentc add
Record Kind (python_function, sqlpp_query, semantic_search, http_request, prompt): semantic_search
Now building a new tool / prompt file. The output will be saved to: $PROJECT_PATH

# Your semantic search name must be written in snake case.
Name: my_semantic_search

Description: Find product descriptions that are closely related to a collection of tags.

# The bucket, scope, and collection where you created your Vector Search index.
Bucket: my-bucket
Scope: my-scope
Collection: my-collection

# The name of the Vector Search index
Index Name: my-vector-search-index

# The name of the field that holds your vector embeddings
Vector Field: vector

# The name of the field to use for your tool's output results
Text Field: output_text

# The name of the embedding meal you used to generate the vector embeddings in your Vector Search index.
Embedding Model: sentence-transformers/all-MiniLM-L12-v2
Semantic search tool written to: $PROJECT_PATH\my_semantic_search.yaml

record_kind: semantic_search

# The name of the query must be a valid Python identifier - the name cannot include spaces.
name: my_semantic_search

# The description will be used in the docstring for this search's generated Python function.
description: >
    Find product descriptions that are closely related to a collection of tags.

# The inputs used to build a comparable representation for a semantic search.
# Inputs are described using a JSON object that follows the JSON schema standard.
# This field is mandatory, and will be used to build a Pydantic model.
# See https://json-schema.org/learn/getting-started-step-by-step for more info.
input: >
   <<< Replace me with your input type! >>>

# As a supplement to the tool similarity search, users can optionally specify search annotations.
# The values of these annotations MUST be strings (e.g., not 'true', but '"true"').
# This field is optional, and does not have to be present.
# annotations:
#   gdpr_2016_compliant: "false"
#   ccpa_2019_compliant: "true"

# The "secrets" field defines search keys that will be used to query a "secrets" manager.
# Note that these values are NOT the secrets themselves, rather they are used to lookup secrets.
secrets:

  # All Couchbase tools (e.g., semantic search, SQL++) must specify conn_string, username, and password.
  - couchbase:
      conn_string: CB_CONN_STRING
      username: CB_USERNAME
      password: CB_PASSWORD

# Couchbase semantic search tools always involve a vector search.
vector_search:

  # A bucket, scope, and collection must be specified.
  # Semantic search across multiple collections is currently not supported.
  bucket: my-bucket
  scope: my-scope
  collection: my-collection

  # All semantic search operations require that a (FTS) vector index is built.
  # In the future, we will relax this constraint.
  index: my-vector-search-index

  # The vector_field refers to the field the vector index (above) was built on.
  # In the future, we will relax the constraint that an index exists on this field.
  vector_field: vector

  # The text_field is the field name used in the tool output (i.e., the results).
  # In the future, we will support multi-field tool outputs for semantic search.
  text_field: output_text

  # The embedding model used to generate the vector_field.
  # This embedding model field value is directly passed to sentence transformers.
  # In the future, we will add support for other types of embedding models.
  embedding_model: sentence-transformers/all-MiniLM-L12-v2

agentc add
Record Kind (python_function, sqlpp_query, semantic_search, http_request, prompt): http_request
Now building a new tool / prompt file. The output will be saved to: $PROJECT_PATH
Type: http_request

# Your http_request will not be assigned a name like the other tool types. Enter a name to populate the filename only.
Filename: my_http_request

# Do not include the path in your OpenAPI spec filename. 
OpenAPI Filename [NO PATH]: webhook-example.json
HTML request tool written to: $PROJECT_PATH\my_http_request.yaml

record_kind: http_request

# As a supplement to the tool similarity search, users can optionally specify search annotations.
# The values of these annotations MUST be strings (e.g., not 'true', but '"true"').
# This field is optional, and does not have to be present.
# annotations:
#   gdpr_2016_compliant: "false"
#   ccpa_2019_compliant: "true"

open_api:
  filename: webhook-example.json

  # Which OpenAPI operations should be indexed as tools are specified below.
  # This field is mandatory, and each operation is validated against the spec on index.
  operations:

    # All operations must specify a path and a method.
    # 1. The path corresponds to an OpenAPI path object.
    # 2. The method corresponds to GET/POST/PUT/PATCH/DELETE/HEAD/OPTIONS/TRACE.
    # See https://swagger.io/specification/#path-item-object for more information.
    - path: <<< Replace me with a path! >>>
      method: <<< Replace me with a method! >>>

agentc add
Record Kind (python_function, sqlpp_query, semantic_search, http_request, prompt): prompt
Now building a new tool / prompt file. The output will be saved to: $PROJECT_PATH
Type: prompt

# Your raw prompt name must be written in snake case.
Name: my_prompt

Description: This prompt provides instructions for how to find routes between airports.
Raw prompt written to: $PROJECT_PATH\my_prompt.prompt

---
record_kind: prompt

# The name of the prompt must be a valid Python identifier - the name cannot include spaces.
name: my_prompt

# The description will be used indirectly when running semantic searches for prompts.
description: >
    This prompt provides instructions for how to find routes between airports.

# As a supplement to the description similarity search, users can optionally specify search annotations.
# The values of these annotations MUST be strings (e.g., not 'true', but '"true"').
# This field is optional, and does not have to be present.
# annotations:
#  organization: "sequoia"

# A prompt is _generally_ (more often than not) associated with a small collection of tools.
# This field is used at provider time to search the catalog for tools.
# This field is optional, and does not have to be present.
# tools:
#   # Tools can be specified using the same parameters found in Provider.get_tools_for.
#   # For instance, we can condition on the tool name...
#   - name: "find_indirect_routes"
#
#   # ...the tool name and some annotations...
#   - name: "find_direct_routes"
#     annotations: gdpr_2016_compliant = "true"
#
#   # ...or even a semantic search via the tool description.
#   - query: "finding flights by name"
#     limit: 2

# Below the '---' represents the prompt in its entirety.
---
<<< Replace me with your prompt! >>>