Skip to main content

​
similarity_search.query

Performs a semantic search across one or more namespaces.

​
Parameters

​
namespaces
List[str]
required
A list of one or more namespace names to search within.
​
query
Union[str, List[float]]
required
The search query (text or a vector).
​
top_k
int
default:"10"
The maximum number of results to return. Defaults to 10.
​
threshold
Optional[float]
A minimum similarity score (0-1) for results. Defaults to None.
​
kiosk_mode
bool
default:"False"
A flag for stricter filtering. Defaults to False.
Returns: Dict[str, Any] - A dictionary containing the search results under the results key. Raises: NamespaceNotFound, InvalidInputError. Text search across one namespace
Search Example
results = client.similarity_search.query(
    namespaces=["my-faq-documents"],
    query="How long do I have to return an item?",
    top_k=1
)
print(results['results'])

​
Advanced Search Examples

Search across multiple namespaces
Multi-Namespace Search
results = client.similarity_search.query(
    namespaces=["faq-documents", "policy-documents"],
    query="return policy",
    top_k=5,
    threshold=0.7
)

for result in results['results']:
    print(f"ID: {result['id']}")
    print(f"Score: {result['score']:.3f}")
    print(f"Text: {result['text'][:100]}...")
    print("---")

​
answer.generate

Submits a query to a text namespace to get a conversational answer generated by an LLM.

​
Parameters

​
namespace
str
required
The single text namespace to search for context.
​
query
str
required
The user’s question or prompt.
​
top_k
int
default:"5"
Number of search results to use as context. Defaults to 5.
​
ai_model
str
default:"anthropic.claude-v2:1"
The identifier for the LLM to use. Defaults to “anthropic.claude-v2:1”.
​
chat_history
Optional[List[Dict]]
A list of previous conversation turns to maintain context.
​
temperature
float
default:"0.7"
The sampling temperature for the LLM (0-1). Defaults to 0.7.
Returns: Dict[str, Any] - A dictionary containing the answer, model, and other metadata. Raises: NamespaceNotFound, InvalidInputError.
Generate Answer Example
response = client.answer.generate(
    namespace="my-faq-documents",
    query="What is your return policy?",
    top_k=2
)

​
Advanced AI Generation

Maintain conversation context
Conversational AI with History
chat_history = [
    {"role": "user", "content": "What are your business hours?"},
    {"role": "assistant", "content": "Our business hours are Monday to Friday, 9 AM to 5 PM EST."}
]

response = client.answer.generate(
    namespace="customer-support",
    query="What about weekends?",
    chat_history=chat_history,
    temperature=0.5,
    ai_model="anthropic.claude-3-sonnet-20240229-v1:0"
)

print(f"AI Answer: {response['answer']}")
print(f"Model Used: {response['model']}")
print(f"Context Count: {response['contextCount']}")

​
Complete Search & AI Workflow

Complete Search and AI Workflow
from moorcheh_sdk import MoorchehClient
import time

with MoorchehClient() as client:
    namespace = "customer-support"

    # 1. Create namespace and upload support documents
    client.namespace.create(namespace, type="text")

    support_docs = [
        {
            "id": "policy-1",
            "text": "Our return policy allows returns within 30 days of purchase with original receipt.",
            "category": "returns"
        },
        {
            "id": "policy-2",
            "text": "We offer free shipping on orders over $50. Standard shipping takes 3-5 business days.",
            "category": "shipping"
        },
        {
            "id": "hours-1",
            "text": "Our customer service is available Monday-Friday 9AM-5PM EST. We're closed on weekends.",
            "category": "hours"
        }
    ]

    client.documents.upload(namespace, support_docs)
    print("Documents uploaded, waiting for processing...")
    time.sleep(5)

    # 2. Perform searches
    print("\n=== SEARCH RESULTS ===")
    search_results = client.similarity_search.query(
        namespaces=[namespace],
        query="return policy",
        top_k=2
    )

    for result in search_results['results']:
        print(f"Score: {result['score']:.3f} | ID: {result['id']}")
        print(f"Text: {result['text'][:80]}...")
        print()

    # 3. Get AI-generated answers
    print("\n=== AI ANSWERS ===")
    questions = [
        "What is your return policy?",
        "How long does shipping take?",
        "Are you open on weekends?"
    ]

    for question in questions:
        response = client.answer.generate(
            namespace=namespace,
            query=question,
            top_k=1
        )
        print(f"Q: {question}")
        print(f"A: {response['answer']}")
        print()

​
Search Result Structure

Search results contain the following fields:
Search Result Format
{
    'results': [
        {
            'id': 'document-id',
            'score': 0.85,  # Similarity score (0-1)
            'label': 'High Relevance',  # Human-readable relevance
            'text': 'Document content...',
            'metadata': {  # Your custom metadata
                'category': 'faq',
                'author': 'support-team'
            }
        }
    ],
    'execution_time': 0.123,
    'timings': {...},  # Detailed timing breakdown
    'optimization_info': {...}  # Search optimization details
}

​
AI Response Structure

AI generation responses contain:
AI Response Format
{
    'answer': 'Generated answer text...',
    'model': 'anthropic.claude-3-sonnet-20240229-v1:0',
    'contextCount': 3,  # Number of documents used as context
    'query': 'Original user query'
}

​
Best Practices

Search Optimization

  • Use specific, clear queries for better results
  • Set appropriate thresholds to filter low-quality results
  • Use multiple namespaces for comprehensive searches
  • Consider kiosk_mode for production applications

AI Generation

  • Provide clear, specific questions
  • Use chat history for conversational experiences
  • Adjust temperature based on creativity needs
  • Choose appropriate AI models for your use case

​
Error Handling

Robust Search with Error Handling
from moorcheh_sdk import MoorchehClient, NamespaceNotFound, InvalidInputError

try:
    with MoorchehClient() as client:
        results = client.similarity_search.query(
            namespaces=["my-namespace"],
            query="search query",
            top_k=5
        )

        if results['results']:
            print(f"Found {len(results['results'])} results")
        else:
            print("No results found")

except NamespaceNotFound:
    print("One or more namespaces don't exist")
except InvalidInputError as e:
    print(f"Invalid search parameters: {e}")
except Exception as e:
    print(f"Unexpected error: {e}")