From 7a83a981e5601d340d58e84222461cf523554f23 Mon Sep 17 00:00:00 2001
From: Tyler <41713505+Tylersuard@users.noreply.github.com>
Date: Sat, 8 Jul 2023 21:49:56 -0700
Subject: [PATCH 1/4] Add get_all_ids_from_index()

---
 pinecone/index.py | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/pinecone/index.py b/pinecone/index.py
index cd6f22e6..77cedbad 100644
--- a/pinecone/index.py
+++ b/pinecone/index.py
@@ -69,6 +69,41 @@ def __init__(self, index_name: str, pool_threads=1):
         self.user_agent = get_user_agent()
         self._vector_api = VectorOperationsApi(self)
 
+
+    import numpy as np
+    def get_ids_from_query(self,input_vector):
+      "Helper function for get_all_ids_from_index()"
+      print("searching pinecone...")
+      results = index.query(vector=input_vector, top_k=10000,include_values=False)
+      ids = set()
+      print(type(results))
+      for result in results['matches']:
+        ids.add(result['id'])
+      return ids
+
+    def get_all_ids_from_index(index, num_dimensions, namespace=""):
+      """Get all ids for all vectors in the index.
+        
+        Example usage:
+        
+        all_ids = get_all_ids_from_index(index, num_dimensions=1536, namespace="")
+        print(all_ids)"""
+
+      num_vectors = index.describe_index_stats()["namespaces"][namespace]['vector_count']
+      all_ids = set()
+      while len(all_ids) < num_vectors:
+        print("Length of ids list is shorter than the number of total vectors...")
+        input_vector = np.random.rand(num_dimensions).tolist()
+        print("creating random vector...")
+        ids = get_ids_from_query(index,input_vector)
+        print("getting ids from a vector query...")
+        all_ids.update(ids)
+        print("updating ids set...")
+        print(f"Collected {len(all_ids)} ids out of {num_vectors}.")
+    
+      return all_ids
+
+
     @validate_and_convert_errors
     def upsert(self,
                vectors: Union[List[Vector], List[tuple], List[dict]],

From 7411778dd5f027a2968c60281f7d9e65bb426dc4 Mon Sep 17 00:00:00 2001
From: Tyler <41713505+Tylersuard@users.noreply.github.com>
Date: Sat, 8 Jul 2023 21:53:02 -0700
Subject: [PATCH 2/4] Update README.md with code for getting all vector ids

---
 README.md | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/README.md b/README.md
index 272692c6..6e409124 100644
--- a/README.md
+++ b/README.md
@@ -163,6 +163,19 @@ query_response = index.query(
 )
 ```
 
+## Get All Vector IDs
+
+The following example retrieves the ID for every vector in the Index.
+```python
+import pinecone
+
+pinecone.init(api_key="YOUR_API_KEY", environment="us-west1-gcp")
+index = pinecone.Index("example-index")
+
+all_ids = index.get_all_ids_from_index(num_dimensions=1536, namespace="")
+print(all_ids)
+```
+
 ## Delete vectors
 
 The following example deletes vectors by ID.

From fb1d549f910055fae7b420be5c1c7ea53f5421d7 Mon Sep 17 00:00:00 2001
From: Tyler <41713505+Tylersuard@users.noreply.github.com>
Date: Sat, 8 Jul 2023 21:55:19 -0700
Subject: [PATCH 3/4] Update index.py

---
 pinecone/index.py | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/pinecone/index.py b/pinecone/index.py
index 77cedbad..74b3d97d 100644
--- a/pinecone/index.py
+++ b/pinecone/index.py
@@ -69,27 +69,25 @@ def __init__(self, index_name: str, pool_threads=1):
         self.user_agent = get_user_agent()
         self._vector_api = VectorOperationsApi(self)
 
-
-    import numpy as np
     def get_ids_from_query(self,input_vector):
       "Helper function for get_all_ids_from_index()"
       print("searching pinecone...")
-      results = index.query(vector=input_vector, top_k=10000,include_values=False)
+      results = self.query(vector=input_vector, top_k=10000,include_values=False)
       ids = set()
       print(type(results))
       for result in results['matches']:
         ids.add(result['id'])
       return ids
 
-    def get_all_ids_from_index(index, num_dimensions, namespace=""):
+    def get_all_ids_from_index(self, num_dimensions, namespace=""):
       """Get all ids for all vectors in the index.
         
         Example usage:
         
-        all_ids = get_all_ids_from_index(index, num_dimensions=1536, namespace="")
+        all_ids = get_all_ids_from_index(self, num_dimensions=1536, namespace="")
         print(all_ids)"""
 
-      num_vectors = index.describe_index_stats()["namespaces"][namespace]['vector_count']
+      num_vectors = self.describe_index_stats()["namespaces"][namespace]['vector_count']
       all_ids = set()
       while len(all_ids) < num_vectors:
         print("Length of ids list is shorter than the number of total vectors...")

From 4cf2864619521458e64277491c26e30ffd82d84f Mon Sep 17 00:00:00 2001
From: Tyler <41713505+Tylersuard@users.noreply.github.com>
Date: Sat, 8 Jul 2023 21:56:09 -0700
Subject: [PATCH 4/4] Update index.py

---
 pinecone/index.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pinecone/index.py b/pinecone/index.py
index 74b3d97d..c7a5ebb5 100644
--- a/pinecone/index.py
+++ b/pinecone/index.py
@@ -93,7 +93,7 @@ def get_all_ids_from_index(self, num_dimensions, namespace=""):
         print("Length of ids list is shorter than the number of total vectors...")
         input_vector = np.random.rand(num_dimensions).tolist()
         print("creating random vector...")
-        ids = get_ids_from_query(index,input_vector)
+        ids = get_ids_from_query(self, input_vector)
         print("getting ids from a vector query...")
         all_ids.update(ids)
         print("updating ids set...")