gnosisllm-knowledge 0.2.0__py3-none-any.whl → 0.4.0__py3-none-any.whl

gnosisllm_knowledge/services/streaming_pipeline.py

@@ -0,0 +1,334 @@
+"""Streaming indexing pipeline with bounded memory.
+
+This module provides the StreamingIndexingPipeline that orchestrates
+the load -> index pipeline with guaranteed bounded memory usage.
+
+Note:
+    This module is tenant-agnostic. Multi-tenancy should be handled at the
+    API layer by using separate indices per account (e.g.,
+    gnosisllm-{account_id}-knowledge) rather than filtering by account_id.
+    The account_id parameters are deprecated and will be ignored.
+"""
+
+from __future__ import annotations
+
+import logging
+import time
+import warnings
+from dataclasses import dataclass, field
+from typing import TYPE_CHECKING, Any
+
+from gnosisllm_knowledge.core.domain.document import Document, DocumentStatus
+from gnosisllm_knowledge.core.domain.result import IndexResult
+from gnosisllm_knowledge.core.events.emitter import EventEmitter
+from gnosisllm_knowledge.core.events.types import (
+    BatchCompletedEvent,
+    StreamingCompletedEvent,
+    StreamingProgressEvent,
+)
+from gnosisllm_knowledge.core.streaming.pipeline import PipelineConfig
+
+if TYPE_CHECKING:
+    from gnosisllm_knowledge.core.interfaces.indexer import IDocumentIndexer
+    from gnosisllm_knowledge.loaders.sitemap import SitemapLoader
+
+
+@dataclass
+class StreamingProgress:
+    """Progress tracking for streaming operations.
+
+    Attributes:
+        urls_discovered: Total URLs discovered so far.
+        urls_processed: URLs that have been fetched and processed.
+        documents_indexed: Documents successfully indexed.
+        documents_failed: Documents that failed to index.
+        current_phase: Current pipeline phase (discovering, fetching, indexing, completed).
+        memory_estimate_mb: Estimated current memory usage in MB.
+    """
+
+    urls_discovered: int = 0
+    urls_processed: int = 0
+    documents_indexed: int = 0
+    documents_failed: int = 0
+    current_phase: str = "initializing"
+    memory_estimate_mb: float = 0.0
+
+
+@dataclass
+class StreamingPipelineResult:
+    """Result of a streaming pipeline execution.
+
+    Attributes:
+        success: Whether the pipeline completed successfully.
+        indexed_count: Total documents indexed.
+        failed_count: Total documents that failed.
+        urls_processed: Total URLs processed.
+        batches_processed: Number of batches processed.
+        duration_ms: Total duration in milliseconds.
+        errors: List of errors encountered.
+    """
+
+    success: bool
+    indexed_count: int = 0
+    failed_count: int = 0
+    urls_processed: int = 0
+    batches_processed: int = 0
+    duration_ms: float = 0.0
+    errors: list[dict[str, Any]] = field(default_factory=list)
+
+
+class StreamingIndexingPipeline:
+    """Orchestrates streaming load -> index pipeline with bounded memory.
+
+    This pipeline ensures:
+    1. URLs are discovered and processed in batches
+    2. Documents are indexed immediately after fetching
+    3. Memory is freed between batches
+    4. Progress is tracked and emitted as events
+    5. Errors don't stop the entire pipeline
+
+    Memory Guarantees:
+    - URL storage: O(url_batch_size)
+    - Document storage: O(index_batch_size)
+    - In-flight fetches: O(fetch_concurrency * avg_page_size)
+    - Total: Bounded, independent of sitemap size
+
+    Example:
+        ```python
+        pipeline = StreamingIndexingPipeline(
+            loader=sitemap_loader,
+            indexer=opensearch_indexer,
+            config=PipelineConfig(
+                url_batch_size=50,
+                fetch_concurrency=10,
+                index_batch_size=100,
+            ),
+        )
+
+        result = await pipeline.execute(
+            source="https://example.com/sitemap.xml",
+            index_name="knowledge-account123",
+            account_id="account123",
+        )
+        ```
+    """
+
+    def __init__(
+        self,
+        loader: SitemapLoader,
+        indexer: IDocumentIndexer,
+        config: PipelineConfig | None = None,
+        events: EventEmitter | None = None,
+    ) -> None:
+        """Initialize the streaming pipeline.
+
+        Args:
+            loader: Sitemap loader instance.
+            indexer: Document indexer instance.
+            config: Pipeline configuration.
+            events: Event emitter for progress events.
+        """
+        self._loader = loader
+        self._indexer = indexer
+        self._config = config or PipelineConfig()
+        self._events = events or EventEmitter()
+        self._logger = logging.getLogger(__name__)
+        self._progress = StreamingProgress()
+
+    async def execute(
+        self,
+        source: str,
+        index_name: str,
+        *,
+        account_id: str | None = None,
+        collection_id: str | None = None,
+        collection_name: str | None = None,
+        source_id: str | None = None,
+        **options: Any,
+    ) -> IndexResult:
+        """Execute the streaming pipeline.
+
+        Note:
+            This method is tenant-agnostic. Multi-tenancy should be handled
+            at the API layer by using separate indices per account. The
+            account_id parameter is deprecated and will be ignored.
+
+        Args:
+            source: Sitemap URL.
+            index_name: Target OpenSearch index.
+            account_id: Deprecated. This parameter is ignored.
+                Use index isolation (separate index per account) instead.
+            collection_id: Collection within account.
+            collection_name: Collection name for display.
+            source_id: Source identifier.
+            **options: Additional loader options.
+
+        Returns:
+            Aggregated index result.
+        """
+        if account_id is not None:
+            warnings.warn(
+                "account_id parameter is deprecated and will be ignored. "
+                "Use index isolation (separate index per account) instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+        start_time = time.time()
+        self._progress = StreamingProgress(current_phase="starting")
+        await self._emit_progress()
+
+        batch_count = 0
+
+        # Create index callback that enriches and indexes documents
+        async def index_batch(documents: list[Document]) -> IndexResult:
+            nonlocal batch_count
+
+            enriched = [
+                self._enrich_document(
+                    doc,
+                    source=source,
+                    collection_id=collection_id,
+                    collection_name=collection_name,
+                    source_id=source_id,
+                )
+                for doc in documents
+            ]
+
+            batch_start = time.time()
+            result = await self._indexer.bulk_index(enriched, index_name)
+            batch_duration = (time.time() - batch_start) * 1000
+
+            self._progress.documents_indexed += result.indexed_count
+            self._progress.documents_failed += result.failed_count
+            self._progress.current_phase = "indexing"
+            await self._emit_progress()
+
+            # Emit batch completed event
+            self._events.emit(
+                BatchCompletedEvent(
+                    batch_index=batch_count,
+                    success_count=result.indexed_count,
+                    failure_count=result.failed_count,
+                    duration_ms=batch_duration,
+                )
+            )
+            batch_count += 1
+
+            return result
+
+        # Execute streaming load with indexing
+        self._progress.current_phase = "processing"
+        await self._emit_progress()
+
+        try:
+            result = await self._loader.load_streaming_with_indexing(
+                source=source,
+                index_callback=index_batch,
+                url_batch_size=self._config.url_batch_size,
+                doc_batch_size=self._config.index_batch_size,
+                config=self._config,
+                **options,
+            )
+        except Exception as e:
+            self._logger.exception(f"Streaming pipeline failed: {e}")
+            duration_ms = (time.time() - start_time) * 1000
+            return IndexResult(
+                success=False,
+                indexed_count=self._progress.documents_indexed,
+                failed_count=self._progress.documents_failed,
+                error_message=str(e),
+                duration_ms=duration_ms,
+            )
+
+        duration_ms = (time.time() - start_time) * 1000
+        self._progress.current_phase = "completed"
+        await self._emit_progress()
+
+        # Emit completion event
+        self._events.emit(
+            StreamingCompletedEvent(
+                total_urls=self._progress.urls_processed,
+                total_documents=result.indexed_count + result.failed_count,
+                indexed_count=result.indexed_count,
+                failed_count=result.failed_count,
+                duration_ms=duration_ms,
+            )
+        )
+
+        return IndexResult(
+            success=result.failed_count == 0,
+            indexed_count=result.indexed_count,
+            failed_count=result.failed_count,
+            errors=result.errors,
+            duration_ms=duration_ms,
+        )
+
+    def _enrich_document(
+        self,
+        doc: Document,
+        source: str,
+        collection_id: str | None,
+        collection_name: str | None,
+        source_id: str | None,
+        account_id: str | None = None,
+    ) -> Document:
+        """Add source info to document.
+
+        Note:
+            This method is tenant-agnostic. Multi-tenancy should be handled
+            at the API layer by using separate indices per account. The
+            account_id parameter is deprecated and will be ignored.
+
+        Args:
+            doc: Original document.
+            source: Source URL.
+            collection_id: Collection identifier.
+            collection_name: Collection name for display.
+            source_id: Source identifier.
+            account_id: Deprecated. This parameter is ignored.
+                Use index isolation (separate index per account) instead.
+
+        Returns:
+            New Document with source info.
+        """
+        if account_id is not None:
+            warnings.warn(
+                "account_id parameter is deprecated and will be ignored. "
+                "Use index isolation (separate index per account) instead.",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
+        return Document(
+            content=doc.content,
+            source=source,
+            doc_id=doc.doc_id,
+            url=doc.url,
+            title=doc.title,
+            collection_id=collection_id,
+            collection_name=collection_name,
+            source_id=source_id,
+            chunk_index=doc.chunk_index,
+            total_chunks=doc.total_chunks,
+            parent_doc_id=doc.parent_doc_id,
+            status=DocumentStatus.INDEXED,
+            metadata=doc.metadata,
+        )
+
+    async def _emit_progress(self) -> None:
+        """Emit progress event."""
+        await self._events.emit_async(
+            StreamingProgressEvent(
+                urls_discovered=self._progress.urls_discovered,
+                urls_processed=self._progress.urls_processed,
+                documents_indexed=self._progress.documents_indexed,
+                documents_failed=self._progress.documents_failed,
+                phase=self._progress.current_phase,
+                memory_mb=self._progress.memory_estimate_mb,
+            )
+        )
+
+    @property
+    def progress(self) -> StreamingProgress:
+        """Get current progress."""
+        return self._progress

{gnosisllm_knowledge-0.2.0.dist-info → gnosisllm_knowledge-0.4.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gnosisllm-knowledge
-Version: 0.2.0
+Version: 0.4.0
 Summary: Enterprise-grade knowledge loading, indexing, and search for Python
 License: MIT
 Keywords: knowledge-base,rag,semantic-search,vector-search,opensearch,llm,embeddings,enterprise
@@ -41,10 +41,12 @@ Enterprise-grade knowledge loading, indexing, and semantic search library for Py
 
 - **Semantic Search**: Vector-based similarity search using OpenAI embeddings
 - **Hybrid Search**: Combine semantic and keyword (BM25) search for best results
+- **Agentic Search**: AI-powered search with reasoning and natural language answers
+- **Agentic Memory**: Conversational memory with automatic fact extraction
 - **Multiple Loaders**: Load content from websites, sitemaps, and files
 - **Intelligent Chunking**: Sentence-aware text splitting with configurable overlap
 - **OpenSearch Backend**: Production-ready with k-NN vector search
-- **Multi-Tenancy**: Built-in support for account and collection isolation
+- **Multi-Tenancy**: Index isolation for complete tenant separation (tenant-agnostic library)
 - **Event-Driven**: Observer pattern for progress tracking and monitoring
 - **SOLID Architecture**: Clean, maintainable, and extensible codebase
 
@@ -142,14 +144,15 @@ gnosisllm-knowledge load <URL> [OPTIONS]
 
 Options:
   --type         Source type: website, sitemap (auto-detects)
-  --index        Target index name (default: knowledge)
-  --account-id   Multi-tenant account ID
+  --index        Target index name (e.g., knowledge-tenant-123)
   --collection-id Collection grouping ID
   --batch-size   Documents per batch (default: 100)
   --max-urls     Max URLs from sitemap (default: 1000)
   --dry-run      Preview without indexing
 ```
 
+Multi-tenancy is achieved through index isolation. Use `--index` with tenant-specific names (e.g., `--index knowledge-tenant-123`).
+
 ### Search
 
 Search indexed content with multiple modes:
@@ -159,14 +162,15 @@ gnosisllm-knowledge search <QUERY> [OPTIONS]
 
 Options:
   --mode         Search mode: semantic, keyword, hybrid, agentic
-  --index        Index to search (default: knowledge)
+  --index        Index to search (e.g., knowledge-tenant-123)
   --limit        Max results (default: 5)
-  --account-id   Filter by account
   --collection-ids Filter by collections (comma-separated)
   --json         Output as JSON for scripting
   --interactive  Interactive search session
 ```
 
+Multi-tenancy is achieved through index isolation. Use `--index` with tenant-specific names.
+
 ## Architecture
 
 ```
@@ -317,22 +321,81 @@ agent_body = {
 
 ## Multi-Tenancy
 
+This library is **tenant-agnostic**. Multi-tenancy is achieved through **index isolation** - each tenant gets their own OpenSearch index.
+
 ```python
-# Load with tenant isolation
+# The calling application (e.g., API) constructs tenant-specific index names
+index_name = f"knowledge-{account_id}"
+
+# Create Knowledge instance for the tenant
+knowledge = Knowledge.from_opensearch(
+    host="localhost",
+    port=9200,
+    index_prefix=index_name,  # knowledge-tenant-123
+)
+
+# Load content to tenant's isolated index
 await knowledge.load(
     source="https://docs.example.com/sitemap.xml",
-    account_id="tenant-123",
     collection_id="docs",
 )
 
-# Search within tenant
+# Search within tenant's index (no account_id filter needed)
 results = await knowledge.search(
     "query",
-    account_id="tenant-123",
     collection_ids=["docs"],
 )
 ```
 
+**Note**: For audit purposes, you can store `account_id` in document metadata:
+```python
+await knowledge.load(
+    source="https://docs.example.com/sitemap.xml",
+    document_defaults={"metadata": {"account_id": "tenant-123"}},
+)
+```
+
+## Agentic Memory
+
+Conversational memory with automatic fact extraction using OpenSearch's ML Memory plugin.
+
+```bash
+# Setup memory connectors
+gnosisllm-knowledge memory setup --openai-key sk-...
+
+# Create container and store conversations
+gnosisllm-knowledge memory container create my-memory
+gnosisllm-knowledge memory store <container-id> --file messages.json --user-id alice
+gnosisllm-knowledge memory recall <container-id> "user preferences" --user-id alice
+```
+
+```python
+from gnosisllm_knowledge import Memory, MemoryStrategy, StrategyConfig, Message
+
+memory = Memory.from_env()
+
+# Create container with strategies
+container = await memory.create_container(
+    name="agent-memory",
+    strategies=[
+        StrategyConfig(type=MemoryStrategy.SEMANTIC, namespace=["user_id"]),
+    ],
+)
+
+# Store conversation with fact extraction
+await memory.store(
+    container_id=container.id,
+    messages=[Message(role="user", content="I prefer dark mode")],
+    user_id="alice",
+    infer=True,
+)
+
+# Recall memories
+result = await memory.recall(container.id, "preferences", user_id="alice")
+```
+
+See [docs/memory.md](docs/memory.md) for full documentation.
+
 ## Event Tracking
 
 ```python

gnosisllm_knowledge-0.4.0.dist-info/RECORD

@@ -0,0 +1,81 @@
+gnosisllm_knowledge/__init__.py,sha256=Egfn6ROa9OttWweCBVocNCUivKwWfdeFEFgpwAoo_ww,4809
+gnosisllm_knowledge/api/__init__.py,sha256=xVG6wMjbFa7_qDVRKlp43O4f0EQmPr9w3pAOGmmh32U,200
+gnosisllm_knowledge/api/knowledge.py,sha256=sjBXBe__wRdGoawmLfDKw9W2o8efOTy0aDVPbt4SMyQ,33718
+gnosisllm_knowledge/api/memory.py,sha256=BrYWS3fCPaymwjzlnLqAKiCrUuMlUDMod-DcrTaarkQ,28926
+gnosisllm_knowledge/backends/__init__.py,sha256=QkVcZbr-u_vDyGiOMs2jrV1oA21VyCLd6g6aJZcSJxk,927
+gnosisllm_knowledge/backends/memory/__init__.py,sha256=Q_2Fh0-Xs1f7CsNn9V7z8NLW0P7F1owmxZQ4k3fTSXo,238
+gnosisllm_knowledge/backends/memory/indexer.py,sha256=4BotG-jveyEFjw7F8K-Co-to9NlydvyDA67JncRtD_E,11284
+gnosisllm_knowledge/backends/memory/searcher.py,sha256=wCnt_ssfA4YxASjSQ7QnXidTqb0Fk0cYYoqKEuiZBMQ,18591
+gnosisllm_knowledge/backends/opensearch/__init__.py,sha256=wwg3QPVVMLkq5qHUGw_9m6gvXO3hxa-xaBj3_BRJlN4,679
+gnosisllm_knowledge/backends/opensearch/agentic.py,sha256=VT9ubsgNacgHEIibKtC1mOEAFKV8VjZmf1NhH_exMvk,36861
+gnosisllm_knowledge/backends/opensearch/config.py,sha256=9xHMvr5-vnCcGFOPoO2_bbKuB70Gm979BqrhvcKsKm0,8640
+gnosisllm_knowledge/backends/opensearch/indexer.py,sha256=0KGagbZ6lMXat9DMSDQgBM-hckNZtDn_eStSlUxQpGo,16803
+gnosisllm_knowledge/backends/opensearch/mappings.py,sha256=zyUBzSPanGEDMUCDs98X_4uwLqLfRikLIO8ut03oc-w,8279
+gnosisllm_knowledge/backends/opensearch/memory/__init__.py,sha256=9EganuADfP6-1lky1Mk_oogr2d9pCmOFcNUjO7UMVZo,403
+gnosisllm_knowledge/backends/opensearch/memory/client.py,sha256=ho0Sn1lXK7EDy0RR6HXjTX5pekrfRc7Vuo4YfBiElr4,44636
+gnosisllm_knowledge/backends/opensearch/memory/config.py,sha256=astoJqofwhl4KUZ6vTUG-yiG1h5hfpJjYdsBzhKzx_E,4633
+gnosisllm_knowledge/backends/opensearch/memory/setup.py,sha256=0ILimioesxx2GLQ4I3uCA-Nu9Wy09PI-rSA85t8ssLw,10372
+gnosisllm_knowledge/backends/opensearch/queries.py,sha256=cubU6fUCeSA6Ag6uDCgrF_pZAj2BgVVmAot2t5sgbxY,13590
+gnosisllm_knowledge/backends/opensearch/searcher.py,sha256=3WvvIjjrEr4iZbDoBGdEGsgARJagHEe2CDfJak0_Gbs,20192
+gnosisllm_knowledge/backends/opensearch/setup.py,sha256=G9G0KZkz_ZynJjRIRWJImLDEFvQQE2wWRJfq_mlfpIs,59483
+gnosisllm_knowledge/chunking/__init__.py,sha256=XKrk04DqwhhPxxP_SLGnQrVUo2fexmvzuEN9YzO4Jxk,225
+gnosisllm_knowledge/chunking/fixed.py,sha256=LXZhRbYbtg4hQzqrAKyGrM_zmDhqJWXDi6cHOiJlGrM,3905
+gnosisllm_knowledge/chunking/sentence.py,sha256=EqY2Y1dpfNK_qukXQC9QYrKN8b1dqyyX9TZN5bUYGqs,7271
+gnosisllm_knowledge/cli/__init__.py,sha256=G8AO-LwNQqXSKZCFxLiXggOQf-xmNITWVs25xWl_-Cg,564
+gnosisllm_knowledge/cli/app.py,sha256=RX7p6GlqcwtbxxxNkEpEXf-Bhjg00ZEF3DvG446rAeA,27411
+gnosisllm_knowledge/cli/commands/__init__.py,sha256=TGrGl_AxVVXpAv01iO4JCUtWW8wzSQTBtQFj4vPeE0A,303
+gnosisllm_knowledge/cli/commands/agentic.py,sha256=QRNaHPryAQKpeVKA3oXj-Xs3rtYUqmRFddC0K0MO7nY,20674
+gnosisllm_knowledge/cli/commands/load.py,sha256=wpJ8ltfC-iTNn8UGAtM5jlToGob9Ia9jDkbDhub-iy8,20315
+gnosisllm_knowledge/cli/commands/memory.py,sha256=ae6AVcdVqJY3eeGBfZv7GHKeFwue-rkuCd8kULb6kQw,24503
+gnosisllm_knowledge/cli/commands/search.py,sha256=eiXdjAvco7I3jU68VcWVabUEt8VlRyqoPDE61FEZ7wo,15385
+gnosisllm_knowledge/cli/commands/setup.py,sha256=yNNqQsydOuN8qwP_nu1coNEjP94EqJmRLU8pv3hve7U,9428
+gnosisllm_knowledge/cli/display/__init__.py,sha256=hLQ3XCBxw8C5WOT-wu1lqFyrD7FJVPHSWXUZM24Qnjc,155
+gnosisllm_knowledge/cli/display/service.py,sha256=Aq2-xSjLtpmRo7K41ca64yHCB338C1r2lb3jLjvKOyI,19226
+gnosisllm_knowledge/cli/utils/__init__.py,sha256=BlzSMhfXM_x9EAv304krVb_DHvdJaKLrlbb716LKkQI,106
+gnosisllm_knowledge/cli/utils/config.py,sha256=UZm_28ZvdviOTeP_Lr54zt4reZ88yOLAZ2w1WyNefJQ,9573
+gnosisllm_knowledge/core/__init__.py,sha256=yeZYSnaypTdStzt3_FERALGUgfC5fuudTCGixUm1_z0,1827
+gnosisllm_knowledge/core/domain/__init__.py,sha256=2D6L5lSiKI9mBTymwGVg5FHmryQskVs_xaGCrUZejuM,2048
+gnosisllm_knowledge/core/domain/discovery.py,sha256=j26zJSzrjRut8AOEdk6xBhOlc24Zh6CCnjKEwimrlmM,5315
+gnosisllm_knowledge/core/domain/document.py,sha256=YhIPmUx2WB8kwgetuqeTVTMFrJSbPeHrMt0VgsZkLWc,8003
+gnosisllm_knowledge/core/domain/memory.py,sha256=sDdqX9gf8vdm4UXtQ7RUAzppNXvwqvWrDLisZAB8Fg4,13139
+gnosisllm_knowledge/core/domain/result.py,sha256=W667qa7KLYXr1cDR6-bz4AN4oancLxNnb_CpynP_XJ0,6112
+gnosisllm_knowledge/core/domain/search.py,sha256=qZEiCPaCNo_uMonPItnfgen0GVNCgVsOZneIuLS8vuM,10180
+gnosisllm_knowledge/core/domain/source.py,sha256=heMIDGvPgO2I91YFYhAjzYz9PHeXDxK59NQ3pMeR0XY,4491
+gnosisllm_knowledge/core/events/__init__.py,sha256=JoUuAeglHMEodE3aUriNN-TVKFkI9Fboyh31XutL4CI,768
+gnosisllm_knowledge/core/events/emitter.py,sha256=qFANzBtgdnQMVgLFE76rA-4i6Es_7ItaI-JfOl9vrNc,6940
+gnosisllm_knowledge/core/events/types.py,sha256=cT8AeM1YJC8Qd0PO2iJ06TFa4BRLDZr2mYURQNeKPOc,12151
+gnosisllm_knowledge/core/exceptions.py,sha256=CIoxRgcNt-EefmkzAvjJnvGZqn-qQsCx0e_RawYEKWI,16315
+gnosisllm_knowledge/core/interfaces/__init__.py,sha256=NZQNCTI4xWTnS6RyiHU4POv4RyrtgazQ0XVNDUoeUOs,1169
+gnosisllm_knowledge/core/interfaces/agentic.py,sha256=hvBPw3fEHoNVjLLQj3-ZmB2QLfbQTLrOTYoUcr9KFAM,3896
+gnosisllm_knowledge/core/interfaces/chunker.py,sha256=FUu3B6Ent5Zofs1XLWZ0RqevHBbGd7iNRO7pAg2JqdE,1862
+gnosisllm_knowledge/core/interfaces/fetcher.py,sha256=19u2TKE6rDjX-8l7xIRKUqa6DLmZz_RncPy1p0sN3tk,3318
+gnosisllm_knowledge/core/interfaces/indexer.py,sha256=PMm2cPJhkVKuNcyLA35S9yYBIk-bBGI2KlQiEv6bKcc,6546
+gnosisllm_knowledge/core/interfaces/loader.py,sha256=NKq5Yj1Pmbv1I8AUMDtleUCZO5URZFw6kCdx6uLG7Bk,2903
+gnosisllm_knowledge/core/interfaces/memory.py,sha256=xrgPsqSfmj1-Snmyd35b-HOKipI_9N_FWRQklHj6x8I,13057
+gnosisllm_knowledge/core/interfaces/searcher.py,sha256=iuFZ5moiMCRhkWty8171BlpP7Jf-NjYqeArenD-L_4E,5015
+gnosisllm_knowledge/core/interfaces/setup.py,sha256=9DMKVqoNUrWKbS58QCnfwlGk4sD9R5iGe-WLwlW7z-Q,4457
+gnosisllm_knowledge/core/interfaces/streaming.py,sha256=sQuWTch8gMandFG1AY4xUVbVC-gwijzktq_Pj5QexWc,4160
+gnosisllm_knowledge/core/streaming/__init__.py,sha256=-PKIWbSu9bI3X3H8bucjuoqBGBiH0UOvM9OSn9dh1Rs,814
+gnosisllm_knowledge/core/streaming/pipeline.py,sha256=H3_9gAvemZp5AdsbrZ5OTbY9aDAfwsl58eq7vOhA09k,6429
+gnosisllm_knowledge/fetchers/__init__.py,sha256=zCLxr1q6XUSjJERn4GUZ5-zGvzcAEY3UwnmQdWsHMYA,679
+gnosisllm_knowledge/fetchers/config.py,sha256=Aqkr3zu0dixpAWLeHSkd_3is2d24ea70e6RagO1pBBE,4068
+gnosisllm_knowledge/fetchers/http.py,sha256=nQjH1nKTIR65tmbfW6RWaP3pR5JJe4j33cTzSBWHM-E,5133
+gnosisllm_knowledge/fetchers/neoreader.py,sha256=8gyo88KilndbJaAE-co-v40jlpXwb6QQKoNgnKQDfA8,7728
+gnosisllm_knowledge/fetchers/neoreader_discovery.py,sha256=uyJ1VEl683J2QS7TWaPUQLsWRXMvcYp1HKQqSQ5cFAQ,16656
+gnosisllm_knowledge/loaders/__init__.py,sha256=gCQpuv4Op0sLj_MspGA-gzGTCFUflnF9s3PpqEqfQSU,601
+gnosisllm_knowledge/loaders/base.py,sha256=bqFzWFD-jeBXdovAuiRUgLKvl5ExaBoDrS0L9e5JhqY,13020
+gnosisllm_knowledge/loaders/discovery.py,sha256=I_lhJ01Ho0JxU8wNW9yCvP0SSEMimld_FuIL2R_5Vaw,12487
+gnosisllm_knowledge/loaders/discovery_streaming.py,sha256=u7g0XpBjaTww6Tx10rs72XXvUI2brliK1uslS7RmayI,13042
+gnosisllm_knowledge/loaders/factory.py,sha256=BMaTZry4LRQ2gm3Dt6mariZigdqlHas4yXhoBW_VzGs,8197
+gnosisllm_knowledge/loaders/sitemap.py,sha256=2VZ7iSYjjQ_od-FuHl9x6dFB5rj4XToi6RWfFR45O4Y,14349
+gnosisllm_knowledge/loaders/sitemap_streaming.py,sha256=KkkIg_oJxJrjQP88kS_jvqQvCShGE9vTGVVeiAr0VDE,8728
+gnosisllm_knowledge/loaders/website.py,sha256=i54S7X0wTYNw9jJQfaoWFqMkGJkbAJeBv-OFBNjPQ_g,1587
+gnosisllm_knowledge/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+gnosisllm_knowledge/services/__init__.py,sha256=qOn1CjsB25UQ2K1TQIGMBe9-CUrGxAKhBrNh9Awo8n8,273
+gnosisllm_knowledge/services/indexing.py,sha256=xZDsULtEuQBYyJ8EZvK_Kp-Gpr6oD87DeURtg-CY3A0,13000
+gnosisllm_knowledge/services/search.py,sha256=WcoO9LJIqdpmThrv0iKvs0CvNWnB3fBh8kdOKaBLO9I,11992
+gnosisllm_knowledge/services/streaming_pipeline.py,sha256=WaLAoDLdgfiBCoqh6A_Im-m4NNwDvCVNtd6f5WrKJPs,11500
+gnosisllm_knowledge-0.4.0.dist-info/METADATA,sha256=I1hufeDnDOl_UMdIlPmDgjt_4bv63oDfbmmuQv-grXE,16311
+gnosisllm_knowledge-0.4.0.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+gnosisllm_knowledge-0.4.0.dist-info/entry_points.txt,sha256=-4wtWCTX7bT8WessWJyqfkQ99-2aCVuSoTL1S_QpaOo,68
+gnosisllm_knowledge-0.4.0.dist-info/RECORD,,

gnosisllm_knowledge-0.2.0.dist-info/RECORD

@@ -1,64 +0,0 @@
-gnosisllm_knowledge/__init__.py,sha256=4pqB289D-9CG7nTnzLfGLwZFTkmnl9REtOAhyDhKE-g,3675
-gnosisllm_knowledge/api/__init__.py,sha256=YOiYXDvA1UPFKpZve_F-wKxN_NNyyiftHEzqsYmRd0I,129
-gnosisllm_knowledge/api/knowledge.py,sha256=on00xHGBe80xq1q2qtmAFTLrdeWGRUKGP8EUiTKVk0o,16791
-gnosisllm_knowledge/backends/__init__.py,sha256=8O0Lsi7gDVbviUmHFjy2rV4eZ2R354Amq-G2EL2eZtk,708
-gnosisllm_knowledge/backends/memory/__init__.py,sha256=Q_2Fh0-Xs1f7CsNn9V7z8NLW0P7F1owmxZQ4k3fTSXo,238
-gnosisllm_knowledge/backends/memory/indexer.py,sha256=R_Yd1gEplzS01o7QfPxjaAZ21VxjfdvatbgrNsyp5lM,10517
-gnosisllm_knowledge/backends/memory/searcher.py,sha256=k6OGtppC-UsHB8aIhlK3wSASVOPEokfe6LLV1jbmE5M,15547
-gnosisllm_knowledge/backends/opensearch/__init__.py,sha256=wwg3QPVVMLkq5qHUGw_9m6gvXO3hxa-xaBj3_BRJlN4,679
-gnosisllm_knowledge/backends/opensearch/agentic.py,sha256=UJdiVDaxQARigOQz0cVfPrduxF8Oa7EH96lorjwji98,25462
-gnosisllm_knowledge/backends/opensearch/config.py,sha256=P30mOAVpo4bEKNHHP04lX2ttzNXgDbu1i-SfobcURNk,7256
-gnosisllm_knowledge/backends/opensearch/indexer.py,sha256=fkfpCwg7Ka2UwDl2L0V1z9sXlvnQbyYMiFeKk1Q1D1Q,15101
-gnosisllm_knowledge/backends/opensearch/mappings.py,sha256=ssev3HFLf82lB1guzqZ0iDQE1C6ppvG1HNGVjG4vwAU,7873
-gnosisllm_knowledge/backends/opensearch/queries.py,sha256=IEZ_teGqc80OFrzD4XIwUArXRre-UhQWIH2oZnRGvC8,13301
-gnosisllm_knowledge/backends/opensearch/searcher.py,sha256=j6j0kzLSxgDRCk1fkqZ642rAXONLa-hnzZr1qEQ1CKI,11594
-gnosisllm_knowledge/backends/opensearch/setup.py,sha256=mZoHBxMK_WZA63F5PviLvGLeH8CqmAn9XM0FnuJXfrQ,52319
-gnosisllm_knowledge/chunking/__init__.py,sha256=XKrk04DqwhhPxxP_SLGnQrVUo2fexmvzuEN9YzO4Jxk,225
-gnosisllm_knowledge/chunking/fixed.py,sha256=LXZhRbYbtg4hQzqrAKyGrM_zmDhqJWXDi6cHOiJlGrM,3905
-gnosisllm_knowledge/chunking/sentence.py,sha256=EqY2Y1dpfNK_qukXQC9QYrKN8b1dqyyX9TZN5bUYGqs,7271
-gnosisllm_knowledge/cli/__init__.py,sha256=G8AO-LwNQqXSKZCFxLiXggOQf-xmNITWVs25xWl_-Cg,564
-gnosisllm_knowledge/cli/app.py,sha256=4Nm5ccxjNHQw9jy9VH7EJ7-rn138i_fPU1yzaef8ELE,15132
-gnosisllm_knowledge/cli/commands/__init__.py,sha256=TGrGl_AxVVXpAv01iO4JCUtWW8wzSQTBtQFj4vPeE0A,303
-gnosisllm_knowledge/cli/commands/agentic.py,sha256=XGZyDKu2TkNNhetzbDIp5zFbBeLwgSyfFfR3VZgZRQM,19836
-gnosisllm_knowledge/cli/commands/load.py,sha256=RZhLtw2Ba6LCceLTD665QE4QcOm-HBc9D-lEX1ReGLM,13117
-gnosisllm_knowledge/cli/commands/search.py,sha256=lj3kUXmvSZRA_z8utbN2Ph_2NczOuzGkuxILreJuj_o,15326
-gnosisllm_knowledge/cli/commands/setup.py,sha256=7NtGGulAggVVQVvzcDq-YLPZlqpGtdKDnYVXd1KPpiQ,7596
-gnosisllm_knowledge/cli/display/__init__.py,sha256=hLQ3XCBxw8C5WOT-wu1lqFyrD7FJVPHSWXUZM24Qnjc,155
-gnosisllm_knowledge/cli/display/service.py,sha256=klGJtc-w7LhNWUaG530QQIazc6c5t8laIM6bnwdyhlg,17537
-gnosisllm_knowledge/cli/utils/__init__.py,sha256=BlzSMhfXM_x9EAv304krVb_DHvdJaKLrlbb716LKkQI,106
-gnosisllm_knowledge/cli/utils/config.py,sha256=8iGzJfInv83lucAHSDfxA5wbTIzh9MlqB2-xa4vcwJg,7292
-gnosisllm_knowledge/core/__init__.py,sha256=yeZYSnaypTdStzt3_FERALGUgfC5fuudTCGixUm1_z0,1827
-gnosisllm_knowledge/core/domain/__init__.py,sha256=15IWkFNV-VKQnInFxMtY4FYh7pNmjYXDq4MPpSsAoPk,938
-gnosisllm_knowledge/core/domain/document.py,sha256=FYvM4Vi1DQeDIq4OEY94dX9eNMpQCmkDQRHkyYqq_WY,7765
-gnosisllm_knowledge/core/domain/result.py,sha256=xyPfselaG7EMhvmcYjepFOEseM4Mfc15Q1Ciq7KxQFE,5843
-gnosisllm_knowledge/core/domain/search.py,sha256=uMJZhGCQ_kS_R5kb1hN5VNEyGbWkuRL_ON_BR4BoqSM,10569
-gnosisllm_knowledge/core/domain/source.py,sha256=kKmWr3U01sJkfG8jtzAQDzxtVVzUOTSqEJZT5gGlYU8,4493
-gnosisllm_knowledge/core/events/__init__.py,sha256=pqWmPSuZIV3_teyYxGgNOLu8yaEw5jTO7A0tKDTydpE,540
-gnosisllm_knowledge/core/events/emitter.py,sha256=qFANzBtgdnQMVgLFE76rA-4i6Es_7ItaI-JfOl9vrNc,6940
-gnosisllm_knowledge/core/events/types.py,sha256=UtmCxkhSfgpHaeFtl43aarmw-eg84KdLuXMBAttICh0,6636
-gnosisllm_knowledge/core/exceptions.py,sha256=fOnE_w2fqX6uS7PGkyXJxiIWcySXpRhfQtUJVA4AFdw,10367
-gnosisllm_knowledge/core/interfaces/__init__.py,sha256=LpBUW0ABmIMUscNIaX-dVkkarqK2pXr0Gf1rg0TSrtU,775
-gnosisllm_knowledge/core/interfaces/agentic.py,sha256=OrS-3YRJ6Z6j1yAngsAv3B9fN9otmwlEyZ_G_fjDJPY,3600
-gnosisllm_knowledge/core/interfaces/chunker.py,sha256=FUu3B6Ent5Zofs1XLWZ0RqevHBbGd7iNRO7pAg2JqdE,1862
-gnosisllm_knowledge/core/interfaces/fetcher.py,sha256=19u2TKE6rDjX-8l7xIRKUqa6DLmZz_RncPy1p0sN3tk,3318
-gnosisllm_knowledge/core/interfaces/indexer.py,sha256=4a33oyhYetAiQ6TF2u7ICPyjjidGwsrjILJ0i0YZCqY,6166
-gnosisllm_knowledge/core/interfaces/loader.py,sha256=NKq5Yj1Pmbv1I8AUMDtleUCZO5URZFw6kCdx6uLG7Bk,2903
-gnosisllm_knowledge/core/interfaces/searcher.py,sha256=c76SH2DD3EEVmaD6TuVjZu5hP6HjoyawUoiT9aANZz0,4634
-gnosisllm_knowledge/core/interfaces/setup.py,sha256=9DMKVqoNUrWKbS58QCnfwlGk4sD9R5iGe-WLwlW7z-Q,4457
-gnosisllm_knowledge/fetchers/__init__.py,sha256=CiupP4NdIPzWme6SKp--a_wDX1qAy-QBUO_bjoVDFBQ,393
-gnosisllm_knowledge/fetchers/config.py,sha256=msUHhTzCGa-cASzoXeAhXFNrDpY9E1XaDo_gqs2CtrU,2611
-gnosisllm_knowledge/fetchers/http.py,sha256=nQjH1nKTIR65tmbfW6RWaP3pR5JJe4j33cTzSBWHM-E,5133
-gnosisllm_knowledge/fetchers/neoreader.py,sha256=Gc5SqHr9e3zvP9TE_xHmW_iwXcYq0UqDCzob7frkaqM,6637
-gnosisllm_knowledge/loaders/__init__.py,sha256=4XlrhFapi9uWsHUAG2eeQEfc47T75a9GRUXde1dmom4,387
-gnosisllm_knowledge/loaders/base.py,sha256=T5m0zrtn-4lA3nYR6mzswQfPwCnYiRhVogzNBvYK2xA,13089
-gnosisllm_knowledge/loaders/factory.py,sha256=gmUqYT3yTijMLP0XRldFWlgLFWdmdvKrj5WvD3RMZw0,6374
-gnosisllm_knowledge/loaders/sitemap.py,sha256=sbsLYs_EugwJRWXOOawpCy7iB2lu46ZW9_3eNymp33I,9524
-gnosisllm_knowledge/loaders/website.py,sha256=i54S7X0wTYNw9jJQfaoWFqMkGJkbAJeBv-OFBNjPQ_g,1587
-gnosisllm_knowledge/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gnosisllm_knowledge/services/__init__.py,sha256=qOn1CjsB25UQ2K1TQIGMBe9-CUrGxAKhBrNh9Awo8n8,273
-gnosisllm_knowledge/services/indexing.py,sha256=ZVDDV2_Zlv6zmCWg-VSNeczieR7LyNaqzXcaFP-uvsE,12471
-gnosisllm_knowledge/services/search.py,sha256=ft8Q7rtRKqXVZ0c_bVqa01jDaV5UQF51LnrY2ICfC1Q,10156
-gnosisllm_knowledge-0.2.0.dist-info/METADATA,sha256=Q5bOjQAt93BXqPFdSF_3XlZh_6ystmXCX8-hcSIuwpg,14152
-gnosisllm_knowledge-0.2.0.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-gnosisllm_knowledge-0.2.0.dist-info/entry_points.txt,sha256=-4wtWCTX7bT8WessWJyqfkQ99-2aCVuSoTL1S_QpaOo,68
-gnosisllm_knowledge-0.2.0.dist-info/RECORD,,