endee-llamaindex 0.1.2__tar.gz

endee_llamaindex-0.1.2/PKG-INFO

@@ -0,0 +1,140 @@
+Metadata-Version: 2.4
+Name: endee-llamaindex
+Version: 0.1.2
+Summary: Vector Database for Fast ANN Searches
+Home-page: https://endee.io
+Author: Endee Labs
+Author-email: vineet@endee.io
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Requires-Dist: llama-index>=0.12.34
+Requires-Dist: endee>=0.1.2
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Endee LlamaIndex Integration
+
+This package provides an integration between [Endee](https://endeedb.ai) (a vector database) and [LlamaIndex](https://www.llamaindex.ai/), allowing you to use Endee as a vector store backend for LlamaIndex.
+
+## Features
+
+- **Vector Storage**: Use Endee for your LlamaIndex embeddings
+- **Multiple Distance Metrics**: Support for cosine, L2, and inner product distance metrics
+- **Metadata Filtering**: Filter search results based on metadata
+- **High Performance**: Optimized for speed and efficiency
+
+## Installation
+
+```bash
+pip install endee-llamaindex
+```
+
+This will install both the `endee-llamaindex` package and its dependencies (`endee` and `llama-index`).
+
+## Quick Start
+
+```python
+import os
+from llama_index.core.schema import TextNode
+from llama_index.core.vector_stores.types import VectorStoreQuery
+from endee_llamaindex import EndeeVectorStore
+
+# Configure your Endee credentials
+api_token = os.environ.get("ENDEE_API_TOKEN")
+index_name = "my_llamaindex_vectors"
+dimension = 1536  # OpenAI ada-002 embedding dimension
+
+# Initialize the vector store
+vector_store = EndeeVectorStore.from_params(
+    api_token=api_token,
+    index_name=index_name,
+    dimension=dimension,
+    space_type="cosine"
+)
+
+# Create a node with embedding
+node = TextNode(
+    text="This is a sample document",
+    id_="doc1",
+    embedding=[0.1, 0.2, 0.3, ...],  # Your embedding vector
+    metadata={
+        "doc_id": "doc1",
+        "source": "example",
+        "author": "Endee"
+    }
+)
+
+# Add the node to the vector store
+vector_store.add([node])
+
+# Query the vector store
+query = VectorStoreQuery(
+    query_embedding=[0.2, 0.3, 0.4, ...],  # Your query vector
+    similarity_top_k=5
+)
+
+results = vector_store.query(query)
+
+# Process results
+for node, score in zip(results.nodes, results.similarities):
+    print(f"Node ID: {node.node_id}, Similarity: {score}")
+    print(f"Text: {node.text}")
+    print(f"Metadata: {node.metadata}")
+```
+
+## Using with LlamaIndex
+
+```python
+from llama_index.core import VectorStoreIndex, StorageContext
+from llama_index.embeddings.openai import OpenAIEmbedding
+
+# Initialize your nodes or documents
+nodes = [...]  # Your nodes with text but no embeddings yet
+
+# Setup embedding function
+embed_model = OpenAIEmbedding()  # Or any other embedding model
+
+# Initialize Endee vector store
+vector_store = EndeeVectorStore.from_params(
+    api_token=api_token,
+    index_name=index_name,
+    dimension=1536,  # Make sure this matches your embedding dimension
+)
+
+# Create storage context
+storage_context = StorageContext.from_defaults(vector_store=vector_store)
+
+# Create vector index
+index = VectorStoreIndex(
+    nodes, 
+    storage_context=storage_context,
+    embed_model=embed_model
+)
+
+# Query the index
+query_engine = index.as_query_engine()
+response = query_engine.query("Your query here")
+print(response)
+```
+
+## Configuration Options
+
+The `EndeeVectorStore` constructor accepts the following parameters:
+
+- `api_token`: Your Endee API token
+- `index_name`: Name of the Endee index
+- `dimension`: Vector dimension (required when creating a new index)
+- `space_type`: Distance metric, one of "cosine", "l2", or "ip" (default: "cosine")
+- `batch_size`: Number of vectors to insert in a single API call (default: 100)
+- `text_key`: Key to use for storing text in metadata (default: "text")
+- `remove_text_from_metadata`: Whether to remove text from metadata (default: False)

endee_llamaindex-0.1.2/README.md

@@ -0,0 +1,116 @@
+# Endee LlamaIndex Integration
+
+This package provides an integration between [Endee](https://endeedb.ai) (a vector database) and [LlamaIndex](https://www.llamaindex.ai/), allowing you to use Endee as a vector store backend for LlamaIndex.
+
+## Features
+
+- **Vector Storage**: Use Endee for your LlamaIndex embeddings
+- **Multiple Distance Metrics**: Support for cosine, L2, and inner product distance metrics
+- **Metadata Filtering**: Filter search results based on metadata
+- **High Performance**: Optimized for speed and efficiency
+
+## Installation
+
+```bash
+pip install endee-llamaindex
+```
+
+This will install both the `endee-llamaindex` package and its dependencies (`endee` and `llama-index`).
+
+## Quick Start
+
+```python
+import os
+from llama_index.core.schema import TextNode
+from llama_index.core.vector_stores.types import VectorStoreQuery
+from endee_llamaindex import EndeeVectorStore
+
+# Configure your Endee credentials
+api_token = os.environ.get("ENDEE_API_TOKEN")
+index_name = "my_llamaindex_vectors"
+dimension = 1536  # OpenAI ada-002 embedding dimension
+
+# Initialize the vector store
+vector_store = EndeeVectorStore.from_params(
+    api_token=api_token,
+    index_name=index_name,
+    dimension=dimension,
+    space_type="cosine"
+)
+
+# Create a node with embedding
+node = TextNode(
+    text="This is a sample document",
+    id_="doc1",
+    embedding=[0.1, 0.2, 0.3, ...],  # Your embedding vector
+    metadata={
+        "doc_id": "doc1",
+        "source": "example",
+        "author": "Endee"
+    }
+)
+
+# Add the node to the vector store
+vector_store.add([node])
+
+# Query the vector store
+query = VectorStoreQuery(
+    query_embedding=[0.2, 0.3, 0.4, ...],  # Your query vector
+    similarity_top_k=5
+)
+
+results = vector_store.query(query)
+
+# Process results
+for node, score in zip(results.nodes, results.similarities):
+    print(f"Node ID: {node.node_id}, Similarity: {score}")
+    print(f"Text: {node.text}")
+    print(f"Metadata: {node.metadata}")
+```
+
+## Using with LlamaIndex
+
+```python
+from llama_index.core import VectorStoreIndex, StorageContext
+from llama_index.embeddings.openai import OpenAIEmbedding
+
+# Initialize your nodes or documents
+nodes = [...]  # Your nodes with text but no embeddings yet
+
+# Setup embedding function
+embed_model = OpenAIEmbedding()  # Or any other embedding model
+
+# Initialize Endee vector store
+vector_store = EndeeVectorStore.from_params(
+    api_token=api_token,
+    index_name=index_name,
+    dimension=1536,  # Make sure this matches your embedding dimension
+)
+
+# Create storage context
+storage_context = StorageContext.from_defaults(vector_store=vector_store)
+
+# Create vector index
+index = VectorStoreIndex(
+    nodes, 
+    storage_context=storage_context,
+    embed_model=embed_model
+)
+
+# Query the index
+query_engine = index.as_query_engine()
+response = query_engine.query("Your query here")
+print(response)
+```
+
+## Configuration Options
+
+The `EndeeVectorStore` constructor accepts the following parameters:
+
+- `api_token`: Your Endee API token
+- `index_name`: Name of the Endee index
+- `dimension`: Vector dimension (required when creating a new index)
+- `space_type`: Distance metric, one of "cosine", "l2", or "ip" (default: "cosine")
+- `batch_size`: Number of vectors to insert in a single API call (default: 100)
+- `text_key`: Key to use for storing text in metadata (default: "text")
+- `remove_text_from_metadata`: Whether to remove text from metadata (default: False)

endee_llamaindex-0.1.2/endee_llamaindex/__init__.py

@@ -0,0 +1,3 @@
+from endee_llamaindex.base import EndeeVectorStore
+
+__all__ = ["EndeeVectorStore"]

endee_llamaindex-0.1.2/endee_llamaindex/base.py

@@ -0,0 +1,416 @@
+import logging
+from collections import Counter
+from functools import partial
+import json
+from typing import Any, Callable, Dict, List, Optional, cast
+
+from llama_index.core.bridge.pydantic import PrivateAttr
+from llama_index.core.schema import BaseNode, MetadataMode, TextNode
+from llama_index.core.vector_stores.types import (
+    BasePydanticVectorStore,
+    MetadataFilters,
+    VectorStoreQuery,
+    VectorStoreQueryMode,
+    VectorStoreQueryResult,
+)
+from llama_index.core.vector_stores.utils import (
+    DEFAULT_TEXT_KEY,
+    legacy_metadata_dict_to_node,
+    metadata_dict_to_node,
+    node_to_metadata_dict,
+)
+
+from datetime import datetime
+
+def _import_endee() -> Any:
+    """
+    Try to import endee module. If it's not already installed, instruct user how to install.
+    """
+    try:
+        import endee
+        from endee.endee_client import Endee
+    except ImportError as e:
+        raise ImportError(
+            "Could not import endee python package. "
+            "Please install it with `pip install endee`."
+        ) from e
+    return endee
+
+ID_KEY = "id"
+VECTOR_KEY = "values"
+SPARSE_VECTOR_KEY = "sparse_values"
+METADATA_KEY = "metadata"
+
+DEFAULT_BATCH_SIZE = 100
+
+_logger = logging.getLogger(__name__)
+
+from llama_index.core.vector_stores.types import MetadataFilter, FilterOperator
+
+reverse_operator_map = {
+    FilterOperator.EQ: "$eq",
+    FilterOperator.NE: "$ne",
+    FilterOperator.GT: "$gt",
+    FilterOperator.GTE: "$gte",
+    FilterOperator.LT: "$lt",
+    FilterOperator.LTE: "$lte",
+    FilterOperator.IN: "$in",
+    FilterOperator.NIN: "$nin",
+}
+
+
+
+def build_dict(input_batch: List[List[int]]) -> List[Dict[str, Any]]:
+    """
+    Build a list of sparse dictionaries from a batch of input_ids.
+
+    NOTE: taken from https://www.pinecone.io/learn/hybrid-search-intro/.
+
+    """
+    # store a batch of sparse embeddings
+    sparse_emb = []
+    # iterate through input batch
+    for token_ids in input_batch:
+        indices = []
+        values = []
+        # convert the input_ids list to a dictionary of key to frequency values
+        d = dict(Counter(token_ids))
+        for idx in d:
+            indices.append(idx)
+            values.append(float(d[idx]))
+        sparse_emb.append({"indices": indices, "values": values})
+    # return sparse_emb list
+    return sparse_emb
+
+
+def generate_sparse_vectors(
+    context_batch: List[str], tokenizer: Callable
+) -> List[Dict[str, Any]]:
+    """
+    Generate sparse vectors from a batch of contexts.
+
+    NOTE: taken from https://www.pinecone.io/learn/hybrid-search-intro/.
+
+    """
+    # create batch of input_ids
+    inputs = tokenizer(context_batch)["input_ids"]
+    # create sparse dictionaries
+    return build_dict(inputs)
+
+
+import_err_msg = (
+    "`endee` package not found, please run `pip install endee` to install it.`"
+)
+
+
+class EndeeVectorStore(BasePydanticVectorStore):
+
+    stores_text: bool = True
+    flat_metadata: bool = False
+
+    api_token: Optional[str]
+    index_name: Optional[str]
+    space_type: Optional[str]
+    dimension: Optional[int]
+    insert_kwargs: Optional[Dict]
+    add_sparse_vector: bool
+    text_key: str
+    batch_size: int
+    remove_text_from_metadata: bool
+
+    _endee_index: Any = PrivateAttr()
+
+    def __init__(
+        self,
+        endee_index: Optional[Any] = None,
+        api_token: Optional[str] = None,
+        index_name: Optional[str] = None,
+        space_type: Optional[str] = "cosine",
+        dimension: Optional[int] = None,
+        insert_kwargs: Optional[Dict] = None,
+        add_sparse_vector: bool = False,
+        text_key: str = DEFAULT_TEXT_KEY,
+        batch_size: int = DEFAULT_BATCH_SIZE,
+        remove_text_from_metadata: bool = False,
+        **kwargs: Any,
+    ) -> None:
+        insert_kwargs = insert_kwargs or {}
+
+        super().__init__(
+            index_name=index_name,
+            api_token=api_token,
+            space_type=space_type,
+            dimension=dimension,
+            insert_kwargs=insert_kwargs,
+            add_sparse_vector=add_sparse_vector,
+            text_key=text_key,
+            batch_size=batch_size,
+            remove_text_from_metadata=remove_text_from_metadata,
+        )
+
+        # Use existing endee_index or initialize a new one
+        self._endee_index = endee_index or self._initialize_endee_index(
+            api_token, index_name, dimension, space_type
+        )
+
+    @classmethod
+    def _initialize_endee_index(
+        cls,
+        api_token: Optional[str],
+        index_name: Optional[str],
+        dimension: Optional[int] = None,
+        space_type: Optional[str] = "cosine",
+    ) -> Any:
+        """Initialize Endee index using the current API."""
+        endee = _import_endee()
+        from endee.endee_client import Endee
+
+        # Initialize Endee client
+        nd = Endee(token=api_token)
+
+        try:
+            # Try to get existing index
+            index = nd.get_index(name=index_name)
+            _logger.info(f"Retrieved existing index: {index_name}")
+            return index
+        except Exception as e:
+            if dimension is None:
+                raise ValueError(
+                    "Must provide dimension when creating a new index"
+                ) from e
+            
+            # Create a new index if it doesn't exist
+            _logger.info(f"Creating new index: {index_name}")
+            nd.create_index(
+                name=index_name,
+                dimension=dimension,
+                space_type=space_type,
+            )
+            return nd.get_index(name=index_name)
+
+    @classmethod
+    def from_params(
+        cls,
+        api_token: Optional[str] = None,
+        index_name: Optional[str] = None,
+        dimension: Optional[int] = None,
+        space_type: str = "cosine",
+        batch_size: int = DEFAULT_BATCH_SIZE,
+    ) -> "EndeeVectorStore":
+        """Create EndeeVectorStore from parameters."""
+        endee_index = cls._initialize_endee_index(
+            api_token, index_name, dimension, space_type
+        )
+
+        return cls(
+            endee_index=endee_index,
+            api_token=api_token,
+            index_name=index_name,
+            dimension=dimension,
+            space_type=space_type,
+            batch_size=batch_size,
+        )
+
+    @classmethod
+    def class_name(cls) -> str:
+        return "EndeeVectorStore"
+
+    def add(
+        self,
+        nodes: List[BaseNode],
+        **add_kwargs: Any,
+    ) -> List[str]:
+        """
+        Add nodes to index.
+
+        Args:
+            nodes: List[BaseNode]: list of nodes with embeddings
+        """
+        ids = []
+        entries = []
+        
+        for node in nodes:
+            node_id = node.node_id
+            metadata = node_to_metadata_dict(node)
+            
+            # Filter values must be simple key-value pairs
+            filter_data = {}
+            if "file_name" in metadata:
+                filter_data["file_name"] = metadata["file_name"]
+            if "doc_id" in metadata:
+                filter_data["doc_id"] = metadata["doc_id"]
+            if "category" in metadata:
+                filter_data["category"] = metadata["category"]
+            if "difficulty" in metadata:
+                filter_data["difficulty"] = metadata["difficulty"]
+            if "language" in metadata:
+                filter_data["language"] = metadata["language"]
+            if "field" in metadata:
+                filter_data["field"] = metadata["field"]
+            if "type" in metadata:
+                filter_data["type"] = metadata["type"]
+            if "feature" in metadata:
+                filter_data["feature"] = metadata["feature"]
+
+            
+            entry = {
+                "id": node_id,
+                "vector": node.get_embedding(),
+                "meta": metadata,
+                "filter": filter_data
+            }
+
+            ids.append(node_id)
+            entries.append(entry)
+        
+        # Batch insert to avoid hitting API limits
+        batch_size = self.batch_size
+        for i in range(0, len(entries), batch_size):
+            batch = entries[i : i + batch_size]
+            self._endee_index.upsert(batch)
+        
+        return ids
+
+    def delete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
+        """
+        Delete nodes using with ref_doc_id.
+        
+        Args:
+            ref_doc_id (str): The id of the document to delete.
+        """
+        try:
+            self._endee_index.delete_with_filter({"doc_id": ref_doc_id})
+        except Exception as e:
+            _logger.error(f"Error deleting vectors for doc_id {ref_doc_id}: {e}")
+
+    @property
+    def client(self) -> Any:
+        """Return Endee index client."""
+        return self._endee_index
+
+    def query(self, query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult:
+        """
+        Query index for top k most similar nodes.
+
+        Args:
+            query: VectorStoreQuery object containing query parameters
+        """
+        if not hasattr(self._endee_index, 'dimension'):
+            # Get dimension from index if available, otherwise try to infer from query
+            try:
+                dimension = self._endee_index.describe()["dimension"]
+            except:
+                if query.query_embedding is not None:
+                    dimension = len(query.query_embedding)
+                else:
+                    raise ValueError("Could not determine vector dimension")
+        else:
+            dimension = self._endee_index.dimension
+        
+        query_embedding = [0.0] * dimension  # Default empty vector
+        filters = {}
+
+        # Apply any metadata filters if provided
+        if query.filters is not None:
+            for filter_item in query.filters.filters:
+                # Case 1: MetadataFilter object
+                if hasattr(filter_item, "key") and hasattr(filter_item, "value") and hasattr(filter_item, "operator"):
+                    op_symbol = reverse_operator_map.get(filter_item.operator)
+                    if not op_symbol:
+                        raise ValueError(f"Unsupported filter operator: {filter_item.operator}")
+                    
+                    if filter_item.key not in filters:
+                        filters[filter_item.key] = {}
+
+                    filters[filter_item.key][op_symbol] = filter_item.value
+
+                # Case 2: Raw dict, e.g. {"category": {"$eq": "programming"}}
+                elif isinstance(filter_item, dict):
+                    for key, op_dict in filter_item.items():
+                        if isinstance(op_dict, dict):
+                            for op, val in op_dict.items():
+                                if key not in filters:
+                                    filters[key] = {}
+                                filters[key][op] = val
+                else:
+                    raise ValueError(f"Unsupported filter format: {filter_item}")
+
+        _logger.info(f"Final structured filters: {filters}")
+
+        # Use the query embedding if provided
+        if query.query_embedding is not None:
+            query_embedding = cast(List[float], query.query_embedding)
+            if query.alpha is not None and query.mode == VectorStoreQueryMode.HYBRID:
+                # Apply alpha scaling in hybrid mode
+                query_embedding = [v * query.alpha for v in query_embedding]
+
+        # Execute query
+        try:
+            results = self._endee_index.query(
+                vector=query_embedding,
+                top_k=query.similarity_top_k,
+                filter=filters if filters else None,
+                include_vectors=True
+            )
+        except Exception as e:
+            _logger.error(f"Error querying Endee: {e}")
+            return VectorStoreQueryResult(nodes=[], similarities=[], ids=[])
+
+        # Process results
+        nodes = []
+        similarities = []
+        ids = []
+
+        for result in results:
+            node_id = result["id"]
+            score = result["similarity"]
+            
+            # Get metadata from result
+            metadata = result.get("meta", {})
+            
+            # Create node from metadata
+            if self.flat_metadata:
+                node = metadata_dict_to_node(
+                    metadata=metadata,
+                    text=metadata.pop(self.text_key, None),
+                    id_=node_id,
+                )
+            else:
+                metadata_dict, node_info, relationships = legacy_metadata_dict_to_node(
+                    metadata=metadata,
+                    text_key=self.text_key,
+                )
+                
+                # Create TextNode with the extracted metadata
+                # Step 1: Get the JSON string from "_node_content"
+                _node_content_str = metadata.get("_node_content", "{}")
+
+                # Step 2: Convert JSON string to Python dict
+                try:
+                    node_content = json.loads(_node_content_str)
+                except json.JSONDecodeError:
+                    node_content = {}
+
+                # Step 3: Get the text
+                text = node_content.get(self.text_key, "")
+                node = TextNode(
+                    text=text,
+                    metadata=metadata_dict,
+                    relationships=relationships,
+                    node_id=node_id,
+                )
+                
+                # Add any node_info properties to the node
+                for key, val in node_info.items():
+                    if hasattr(node, key):
+                        setattr(node, key, val)
+            
+            # If embedding was returned in the results, add it to the node
+            if "vector" in result:
+                node.embedding = result["vector"]
+            
+            nodes.append(node)
+            similarities.append(score)
+            ids.append(node_id)
+
+        return VectorStoreQueryResult(nodes=nodes, similarities=similarities, ids=ids)

endee_llamaindex-0.1.2/endee_llamaindex.egg-info/PKG-INFO

@@ -0,0 +1,140 @@
+Metadata-Version: 2.4
+Name: endee-llamaindex
+Version: 0.1.2
+Summary: Vector Database for Fast ANN Searches
+Home-page: https://endee.io
+Author: Endee Labs
+Author-email: vineet@endee.io
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+Requires-Dist: llama-index>=0.12.34
+Requires-Dist: endee>=0.1.2
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Endee LlamaIndex Integration
+
+This package provides an integration between [Endee](https://endeedb.ai) (a vector database) and [LlamaIndex](https://www.llamaindex.ai/), allowing you to use Endee as a vector store backend for LlamaIndex.
+
+## Features
+
+- **Vector Storage**: Use Endee for your LlamaIndex embeddings
+- **Multiple Distance Metrics**: Support for cosine, L2, and inner product distance metrics
+- **Metadata Filtering**: Filter search results based on metadata
+- **High Performance**: Optimized for speed and efficiency
+
+## Installation
+
+```bash
+pip install endee-llamaindex
+```
+
+This will install both the `endee-llamaindex` package and its dependencies (`endee` and `llama-index`).
+
+## Quick Start
+
+```python
+import os
+from llama_index.core.schema import TextNode
+from llama_index.core.vector_stores.types import VectorStoreQuery
+from endee_llamaindex import EndeeVectorStore
+
+# Configure your Endee credentials
+api_token = os.environ.get("ENDEE_API_TOKEN")
+index_name = "my_llamaindex_vectors"
+dimension = 1536  # OpenAI ada-002 embedding dimension
+
+# Initialize the vector store
+vector_store = EndeeVectorStore.from_params(
+    api_token=api_token,
+    index_name=index_name,
+    dimension=dimension,
+    space_type="cosine"
+)
+
+# Create a node with embedding
+node = TextNode(
+    text="This is a sample document",
+    id_="doc1",
+    embedding=[0.1, 0.2, 0.3, ...],  # Your embedding vector
+    metadata={
+        "doc_id": "doc1",
+        "source": "example",
+        "author": "Endee"
+    }
+)
+
+# Add the node to the vector store
+vector_store.add([node])
+
+# Query the vector store
+query = VectorStoreQuery(
+    query_embedding=[0.2, 0.3, 0.4, ...],  # Your query vector
+    similarity_top_k=5
+)
+
+results = vector_store.query(query)
+
+# Process results
+for node, score in zip(results.nodes, results.similarities):
+    print(f"Node ID: {node.node_id}, Similarity: {score}")
+    print(f"Text: {node.text}")
+    print(f"Metadata: {node.metadata}")
+```
+
+## Using with LlamaIndex
+
+```python
+from llama_index.core import VectorStoreIndex, StorageContext
+from llama_index.embeddings.openai import OpenAIEmbedding
+
+# Initialize your nodes or documents
+nodes = [...]  # Your nodes with text but no embeddings yet
+
+# Setup embedding function
+embed_model = OpenAIEmbedding()  # Or any other embedding model
+
+# Initialize Endee vector store
+vector_store = EndeeVectorStore.from_params(
+    api_token=api_token,
+    index_name=index_name,
+    dimension=1536,  # Make sure this matches your embedding dimension
+)
+
+# Create storage context
+storage_context = StorageContext.from_defaults(vector_store=vector_store)
+
+# Create vector index
+index = VectorStoreIndex(
+    nodes, 
+    storage_context=storage_context,
+    embed_model=embed_model
+)
+
+# Query the index
+query_engine = index.as_query_engine()
+response = query_engine.query("Your query here")
+print(response)
+```
+
+## Configuration Options
+
+The `EndeeVectorStore` constructor accepts the following parameters:
+
+- `api_token`: Your Endee API token
+- `index_name`: Name of the Endee index
+- `dimension`: Vector dimension (required when creating a new index)
+- `space_type`: Distance metric, one of "cosine", "l2", or "ip" (default: "cosine")
+- `batch_size`: Number of vectors to insert in a single API call (default: 100)
+- `text_key`: Key to use for storing text in metadata (default: "text")
+- `remove_text_from_metadata`: Whether to remove text from metadata (default: False)

endee_llamaindex-0.1.2/endee_llamaindex.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+README.md
+setup.py
+endee_llamaindex/__init__.py
+endee_llamaindex/base.py
+endee_llamaindex.egg-info/PKG-INFO
+endee_llamaindex.egg-info/SOURCES.txt
+endee_llamaindex.egg-info/dependency_links.txt
+endee_llamaindex.egg-info/requires.txt
+endee_llamaindex.egg-info/top_level.txt

endee_llamaindex-0.1.2/endee_llamaindex.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

endee_llamaindex-0.1.2/endee_llamaindex.egg-info/requires.txt

@@ -0,0 +1,2 @@
+llama-index>=0.12.34
+endee>=0.1.2

endee_llamaindex-0.1.2/endee_llamaindex.egg-info/top_level.txt

@@ -0,0 +1 @@
+endee_llamaindex

endee_llamaindex-0.1.2/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

endee_llamaindex-0.1.2/setup.py

@@ -0,0 +1,26 @@
+# myproject/setup.py
+
+from setuptools import setup, find_packages
+
+setup(
+    name="endee-llamaindex",
+    version="0.1.2",
+    packages=find_packages(include=['endee_llamaindex', 'endee_llamaindex.*']),
+    install_requires=[
+        # List your dependencies here
+        "llama-index>=0.12.34",
+        "endee>=0.1.2",
+    ],
+    author="Endee Labs",
+    author_email="vineet@endee.io",
+    description="Vector Database for Fast ANN Searches",
+    long_description=open('README.md').read(),
+    long_description_content_type="text/markdown",
+    url="https://endee.io",
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires='>=3.6',
+)