Add target/named vector support to QA

[cdpierse]

• Adds support to QueryAgents run() method to support the target_vector argument which is to be used in cases where a underlying collection is configured using named vectors
• If the constructor for the QA consists of multiple collections then the structure of target_vector must be a dict mapping of collection names to the underlying target vector name for example:

# Assume `client` is your WeaviateClient instance
agent = QueryAgent(
    client,
    collections=["collection1", "collection2"],
)

# Specify a target vector for each collection
target_vector = {
    "collection1": "vectorA",
    "collection2": "vectorB"
}

response = agent.run("your query here", target_vector=target_vector)

[orca-security-eu]

Orca Security Scan Summary

Status	Check	Issues by priority
Passed	Infrastructure as Code	0   0   0   0	View in Orca
Passed	SAST	0   0   0   0	View in Orca
Passed	Secrets	0   0   0   0	View in Orca
Passed	Vulnerabilities	0   0   0   0	View in Orca