ragit 0.3__py3-none-any.whl → 0.10.1__py3-none-any.whl

ragit/main.py

@@ -1,384 +0,0 @@
-import chromadb
-import pandas as pd
-import logging
-from sentence_transformers import SentenceTransformer
-from typing import List, Dict, Optional, Union
-import os
-
-
-class VectorDBManager:
-    def __init__(
-        self,
-        persist_directory: str = "./vector_db",
-        provider: str = "sentence_transformer",
-        model_name: str = "all-mpnet-base-v2",
-    ):
-        """
-        Initialize the Vector Database Manager.
-
-        Args:
-            persist_directory (str): Directory to persist the database
-        """
-        self.persist_directory = persist_directory
-        self.client = chromadb.PersistentClient(path=persist_directory)
-        if provider == "sentence_transformer":
-            self.model = SentenceTransformer(model_name)
-
-        logging.basicConfig(
-            level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
-        )
-        self.logger = logging.getLogger(__name__)
-
-    def create_database(
-        self,
-        csv_path: str,
-        collection_name: str,
-        distance_metric: str = "l2",
-        collection_metadata: Dict = None,
-    ) -> bool:
-        """
-        Create a new database from a CSV file.
-
-        Args:
-            csv_path (str): Path to the CSV file containing 'id' and 'text' columns
-            collection_name (str): Name of the collection to create
-            distance_metric (str): Distance metric (l2, cosine, ip)
-            collection_metadata (Dict, optional): Additional metadata for the collection
-
-        Returns:
-            bool: True if successful, False otherwise
-        """
-        try:
-
-            df = pd.read_csv(csv_path)
-
-            if not {"id", "text"}.issubset(df.columns):
-                self.logger.error("CSV must contain 'id' and 'text' columns")
-                return False
-
-            collection_meta = {
-                "hnsw:space": distance_metric,
-                "description": f"Collection created from {csv_path}",
-            }
-
-            if collection_metadata:
-                collection_meta.update(collection_metadata)
-
-            collection = self.client.create_collection(
-                name=collection_name, metadata=collection_meta
-            )
-
-            embeddings = self.model.encode(df["text"].tolist()).tolist()
-
-            collection.add(
-                ids=[str(id_) for id_ in df["id"]],
-                documents=df["text"].tolist(),
-                embeddings=embeddings,
-            )
-
-            self.logger.info(f"Successfully created collection '{collection_name}'")
-            return True
-
-        except Exception as e:
-            self.logger.error(f"Error creating database: {str(e)}")
-            return False
-
-    def add_values_from_csv(
-        self, csv_path: str, collection_name: str
-    ) -> Dict[str, int]:
-        """
-        Add values from CSV file to existing collection, skipping existing IDs.
-
-        Args:
-            csv_path (str): Path to the CSV file
-            collection_name (str): Name of the target collection
-
-        Returns:
-            Dict[str, int]: Statistics about the operation
-        """
-        try:
-
-            df = pd.read_csv(csv_path)
-
-            collection = self.client.get_collection(collection_name)
-
-            existing_ids = set(collection.get()["ids"])
-
-            new_df = df[~df["id"].astype(str).isin(existing_ids)]
-
-            if not new_df.empty:
-
-                embeddings = self.model.encode(new_df["text"].tolist()).tolist()
-
-                collection.add(
-                    ids=[str(id_) for id_ in new_df["id"]],
-                    documents=new_df["text"].tolist(),
-                    embeddings=embeddings,
-                )
-
-            stats = {
-                "total_entries": len(df),
-                "new_entries_added": len(new_df),
-                "skipped_entries": len(df) - len(new_df),
-            }
-
-            self.logger.info(
-                f"Added {stats['new_entries_added']} new entries to '{collection_name}'"
-            )
-            return stats
-
-        except Exception as e:
-            self.logger.error(f"Error adding values from CSV: {str(e)}")
-            return {"error": str(e)}
-
-    def add_single_row(self, id_: str, text: str, collection_name: str) -> bool:
-        """
-        Add a single entry to the collection.
-
-        Args:
-            id_ (str): ID for the new entry
-            text (str): Text content
-            collection_name (str): Target collection name
-
-        Returns:
-            bool: True if successful, False otherwise
-        """
-        try:
-            collection = self.client.get_collection(collection_name)
-
-            if str(id_) in collection.get()["ids"]:
-                self.logger.warning(f"ID {id_} already exists in collection")
-                return False
-
-            embedding = self.model.encode([text]).tolist()
-
-            collection.add(ids=[str(id_)], documents=[text], embeddings=embedding)
-
-            self.logger.info(f"Successfully added entry with ID {id_}")
-            return True
-
-        except Exception as e:
-            self.logger.error(f"Error adding single row: {str(e)}")
-            return False
-
-    def delete_entry_by_id(self, id_: str, collection_name: str) -> bool:
-        """
-        Delete an entry by its ID.
-
-        Args:
-            id_ (str): ID of the entry to delete
-            collection_name (str): Collection name
-
-        Returns:
-            bool: True if successful, False otherwise
-        """
-        try:
-            collection = self.client.get_collection(collection_name)
-
-            if str(id_) not in collection.get()["ids"]:
-                self.logger.warning(f"ID {id_} not found in collection")
-                return False
-
-            collection.delete(ids=[str(id_)])
-
-            self.logger.info(f"Successfully deleted entry with ID {id_}")
-            return True
-
-        except Exception as e:
-            self.logger.error(f"Error deleting entry: {str(e)}")
-            return False
-
-    def find_nearby_texts(
-        self,
-        text: str,
-        collection_name: str,
-        search_string: Optional[str] = None,
-        k: int = 5,
-    ) -> List[Dict[str, Union[str, float]]]:
-        """
-        Find nearby texts using similarity search with scores.
-
-        Args:
-            text (str): Query text
-            collection_name (str): Collection to search in
-            k (int): Number of results to return
-
-        Returns:
-            List[Dict[str, Union[str, float]]]: List of nearby texts with their IDs and similarity scores
-        """
-        try:
-            collection = self.client.get_collection(collection_name)
-            print("Metadata:", collection.metadata)
-
-            distance_metric = collection.metadata["hnsw:space"]
-
-            query_embedding = self.model.encode([text]).tolist()
-
-            if search_string:
-                results = collection.query(
-                    query_embeddings=query_embedding,
-                    n_results=k,
-                    include=["documents", "distances", "metadatas"],
-                    where_document={"$contains": search_string},
-                )
-            else:
-                results = collection.query(
-                    query_embeddings=query_embedding,
-                    n_results=k,
-                    include=["documents", "distances", "metadatas"],
-                )
-
-            distances = results["distances"][0]
-            if not distances:
-                return []
-
-            similarities = []
-            for dist in distances:
-                if distance_metric == "cosine":
-
-                    similarity = 1 - dist
-                elif distance_metric == "ip":
-
-                    min_dist = min(distances)
-                    max_dist = max(distances)
-                    similarity = (
-                        (dist - min_dist) / (max_dist - min_dist)
-                        if max_dist > min_dist
-                        else 1.0
-                    )
-                elif distance_metric == "l1":
-
-                    max_dist = max(distances)
-                    similarity = 1 - (dist / max_dist) if max_dist > 0 else 1.0
-                elif distance_metric == "l2":
-
-                    max_dist = max(distances)
-                    similarity = 1 - (dist / max_dist) if max_dist > 0 else 1.0
-
-                similarities.append(similarity)
-
-            nearby_texts = [
-                {
-                    "id": id_,
-                    "text": text_,
-                    "similarity": round(similarity * 100, 4),
-                    "raw_distance": dist,
-                    "metric": distance_metric,
-                }
-                for id_, text_, similarity, dist in zip(
-                    results["ids"][0], results["documents"][0], similarities, distances
-                )
-            ]
-
-            return nearby_texts
-
-        except Exception as e:
-            self.logger.error(f"Error finding nearby texts: {str(e)}")
-            return []
-
-    def delete_collection(self, collection_name: str, confirmation: str = "no") -> bool:
-        """
-        Delete an entire collection.
-
-        Args:
-            collection_name (str): Name of collection to delete
-            confirmation (str): Must be 'yes' to proceed
-
-        Returns:
-            bool: True if successful, False otherwise
-        """
-        try:
-            if confirmation.lower() != "yes":
-                self.logger.warning("Deletion cancelled - confirmation not provided")
-                return False
-
-            self.client.delete_collection(collection_name)
-            self.logger.info(f"Successfully deleted collection '{collection_name}'")
-            return True
-
-        except Exception as e:
-            self.logger.error(f"Error deleting collection: {str(e)}")
-            return False
-
-    def get_collection_info(self, collection_name: str) -> Dict:
-        """
-        Get information about a collection.
-
-        Args:
-            collection_name (str): Name of the collection
-
-        Returns:
-            Dict: Collection information and statistics
-        """
-        try:
-            collection = self.client.get_collection(collection_name)
-            collection_data = collection.get()
-
-            info = {
-                "name": collection_name,
-                "count": len(collection_data["ids"]),
-                "metadata": collection.metadata,
-            }
-
-            return info
-
-        except Exception as e:
-            self.logger.error(f"Error getting collection info: {str(e)}")
-            return {"error": str(e)}
-
-    def get_by_ids(self, ids: List[str], collection_name: str) -> Dict[str, str]:
-        """
-        Get texts for given IDs in batch.
-
-        Args:
-            ids (List[str]): List of IDs to fetch
-            collection_name (str): Name of the collection
-
-        Returns:
-            Dict[str, str]: Dictionary mapping IDs to their corresponding texts
-        """
-        try:
-            collection = self.client.get_collection(collection_name)
-
-            str_ids = [str(id_) for id_ in ids]
-
-            results = collection.get(ids=str_ids, include=["documents"])
-
-            id_to_text = {
-                id_: text for id_, text in zip(results["ids"], results["documents"])
-            }
-
-            return id_to_text
-
-        except Exception as e:
-            self.logger.error(f"Error getting texts by IDs: {str(e)}")
-            return {}
-
-    def get_by_texts(self, texts: List[str], collection_name: str) -> Dict[str, str]:
-        """
-        Get IDs for given texts in batch.
-        Note: For exact text matching. For similar texts, use find_nearby_texts.
-
-        Args:
-            texts (List[str]): List of texts to fetch
-            collection_name (str): Name of the collection
-
-        Returns:
-            Dict[str, str]: Dictionary mapping texts to their corresponding IDs
-        """
-        try:
-            collection = self.client.get_collection(collection_name)
-
-            all_data = collection.get()
-
-            text_to_id = {
-                text: id_
-                for text, id_ in zip(all_data["documents"], all_data["ids"])
-                if text in texts
-            }
-
-            return text_to_id
-
-        except Exception as e:
-            self.logger.error(f"Error getting IDs by texts: {str(e)}")
-            return {}

ragit-0.3.dist-info/METADATA

@@ -1,163 +0,0 @@
-Metadata-Version: 2.2
-Name: ragit
-Version: 0.3
-Description-Content-Type: text/markdown
-Requires-Dist: sentence-transformers>=3.4.1
-Requires-Dist: pandas>=2.2.3
-Requires-Dist: chromadb>=0.6.3
-Requires-Dist: setuptools>=75.8.0
-Requires-Dist: wheel>=0.45.1
-Requires-Dist: twine>=6.1.0
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: requires-dist
-
-
-# Ragit
-🚀 Smart, Fast, Scalable Search 🚀
-
-Github Repo : [stsfaroz](https://github.com/stsfaroz/ragit)
-
-**ragit** is a lightweight Python library that simplifies the management of vector databases using [ChromaDB](https://github.com/chroma-core/chroma). With ragit, you can easily create, update, query, and manage your vector database—all from CSV files containing text data.
-
-## Features
-
-- **Create a Vector Database:** Build your database from a CSV file with two required columns: `id` and `text`.
-- **Add New Entries:** Insert additional entries from CSV files or add them individually.
-- **Similarity Search:** Find nearby texts using various distance metrics (e.g., cosine, L2) with similarity scores.
-- **Data Retrieval:** Fetch entries by IDs or exact text matches.
-- **Deletion:** Remove single entries or entire collections when needed.
-
-## CSV File Format
-ragit expects your CSV file to have exactly two columns: `id` and `text`.
-
-## Example CSV (`data.csv`):
-
-```csv
-id,text
-1,The quick brown fox jumps over the lazy dog.
-2,Another sample entry for testing.
-```
-
-## Usage
-Below are some examples that demonstrate how to use `ragit`. The examples cover creating a database, adding entries, performing similarity searches, and more.
-
-### 1. Importing and Initializing
-First, import the `VectorDBManager` class from `ragit` and initialize it:
-
-```python
-from ragit import VectorDBManager
-
-# Initialize the vector database manager with a custom persistence directory and model
-db_manager = VectorDBManager(
-    persist_directory="./my_vector_db", # Optional # default : "./vector_db"
-    provider="sentence_transformer", # Optional # default : "sentence_transformer"
-    model_name="all-mpnet-base-v2" # Optional # default : "all-mpnet-base-v2"
-)
-```
-
-### 2. Creating a Database
-Create a new collection (named `my_collection`) using your CSV file. In this example, the `distance_metric` is set to "cosine"(available options: l2, cosine, ip, l1) :
-
-```python
-db_manager.create_database(
-    csv_path="data.csv", 
-    collection_name="my_collection",
-    distance_metric="cosine" # Optional # default : l2
-)
-```
-
-### 3. Adding a Single Entry
-Add an individual entry to the collection:
-
-```python
-db_manager.add_single_row(
-    id_="101",
-    text="This is a new test entry for the database.",
-    collection_name="my_collection"
-)
-```
-
-### 4. Adding Multiple Entries from CSV
-You can also add multiple entries from a CSV file. This function skips any entries that already exist in the collection:
-
-```python
-stats = db_manager.add_values_from_csv(
-    csv_path="data.csv",
-    collection_name="my_collection"
-)
-print(f"Added {stats['new_entries_added']} new entries")
-```
-
-### 5. Retrieving Collection Information
-Fetch and display information about your collection:
-
-```python
-info = db_manager.get_collection_info("my_collection")
-print(f"Collection size: {info['count']} entries")
-```
-
-### 6. Performing a Similarity Search
-Find texts that are similar to your query. In this example, the query text is "ai", and the search is filtered using the string "Artificial intelligence". The top 2 results are returned:
-
-```python
-results = db_manager.find_nearby_texts(
-    text="ai",
-    collection_name="my_collection",
-    k=2,
-    search_string="Artificial intelligence" # Optional
-)
-
-print("Results:")
-for item in results:
-    print(f"\nID: {item['id']}")
-    print(f"Text: {item['text']}")
-    print(f"Similarity: {item['similarity']}%")
-    print(f"Distance ({item['metric']}): {item['raw_distance']}")
-```
-
-### 7. Deleting an Entry
-Remove an entry from the collection by its ID:
-
-```python
-db_manager.delete_entry_by_id(
-    id_="1",
-    collection_name="my_collection"
-)
-```
-
-### 8. Fetching Texts by IDs
-Retrieve text entries for a list of IDs:
-
-```python
-ids_to_fetch = ["1", "2", "3"]
-texts = db_manager.get_by_ids(ids_to_fetch, "my_collection")
-print("Texts:", texts)
-```
-
-### 9. Fetching IDs by Texts
-For an exact text match, get the corresponding IDs:
-
-```python
-texts_to_fetch = [
-    "Plato was an ancient Greek philosopher of the Classical period who is considered a foundational thinker in Western philosophy"
-]
-ids = db_manager.get_by_texts(texts_to_fetch, "my_collection")
-print("IDs:", ids)
-```
-
-### 10. Deleting a Collection
-Delete an entire collection. **Note:** You must pass `confirmation="yes"` to proceed with deletion.
-
-```python
-db_manager.delete_collection(
-    collection_name="my_collection",
-    confirmation="yes"
-)
-```
-
-## Contributing
-Contributions are welcome! If you encounter any issues or have suggestions for improvements, please feel free to open an issue or submit a pull request on GitHub.
-
-## License
-This project is licensed under the MIT License. See the `LICENSE` file for details.

ragit-0.3.dist-info/RECORD

@@ -1,6 +0,0 @@
-ragit/__init__.py,sha256=GECJxYFL_0PMy6tbcVFpW9Fhe1JiI2uXH4iJWhUHpKs,48
-ragit/main.py,sha256=L5jId4Cwrd99tV10QzokvF3XWarOj3vPEOWLzPrTMN0,12721
-ragit-0.3.dist-info/METADATA,sha256=CudjOrPzxSzl46OhIUtL5mhkhhwgkdcWO9UB3nXzuCE,5103
-ragit-0.3.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ragit-0.3.dist-info/top_level.txt,sha256=pkPbG7yrw61wt9_y_xcLE2vq2a55fzockASD0yq0g4s,6
-ragit-0.3.dist-info/RECORD,,