pinecone-retrieval

Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "embed_anything"
 
-version = "0.1.14"
+version = "0.1.15"
 edition = "2021"
 
 [dependencies]

README.md

@@ -12,6 +12,7 @@
 [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1CowJrqZxDDYJzkclI-rbHaZHgL9C6K3p?usp=sharing)
 [![license]( https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 [![license]( https://img.shields.io/badge/Package-PYPI-blue.svg)](https://pypi.org/project/embed-anything/)
+[![license](https://img.shields.io/discord/1223707915827937321?style=flat&logo=discord&link=https%3A%2F%2Fdiscord.gg%2FHGxDZxNt9G)](https://discord.gg/juETVTMdZu)
 
 EmbedAnything is a powerful python library designed to streamline the creation and management of embedding pipelines. Whether you're working with text, images, audio, or any other type of data., EmbedAnything makes it easy to generate embeddings from multiple sources and store them efficiently in a vector database.
 

retrieval.py

@@ -0,0 +1,32 @@
+import embed_anything
+from openai import OpenAI
+
+import os
+import time
+from pinecone import Pinecone
+import numpy as np
+
+
+
+data = embed_anything.embed_directory('Vector_database_files\test_paper.pdf', embeder= "OpenAI")
+embeddings = np.array([data.embedding for data in data])
+
+print(len(data))
+query= embed_anything.embed_query(["what is AI?"], embeder="OpenAI")
+
+pc = Pinecone(api_key="")
+index = pc.Index("anything")
+
+# for i in range(len(data)):
+#     index.upsert(
+#         vectors=[{"id": str(i), "values": data[i].embedding, "metadata": {"text": data[i].text}}]
+#     )
+
+
+
+def retrieval(query):
+    query_embedding = embed_anything.embed_query(query, embeder="OpenAI")
+    return index.query(vector=query_embedding[0].embedding, top_k=2)
+
+
+print(retrieval(["what is AI?"]))