readme and param defaults update (#3)

- Updated `pip install` and examples in README to point to
`sample-data/`
- Updated default value for `initial_cap` param on Vector field
- Updated index deletion function to allow for future behavior
customization

[ committed by @tylerhutcherson ]
[ reviewed by @Spartee ]

Author: tylerhutcherson

README.md

@@ -50,21 +50,22 @@ fields:
 ```
 
 #### Example Usage
+These examples reference [provided sample data](sample-data/).
 
 ```bash
 # load in a pickled dataframe with
-redisvl load -s sample.yml -d embeddings.pkl
+redisvl load -s sample-data/sample.yml -d sample-data/pandas-sample.pkl
 ```
 
 ```bash
 # load in a pickled dataframe to a specific address and port
-redisvl load -s sample.yml -d embeddings.pkl -h 127.0.0.1 -p 6379
+redisvl load -s sample-data/sample.yml -d sample-data/pandas-sample.pkl -h 127.0.0.1 -p 6379
 ```
 
 ```bash
 # load in a pickled dataframe to a specific
 # address and port and with password
-redisvl load -s sample.yml -d embeddings.pkl -h 127.0.0.1 -p 6379 -p supersecret
+redisvl load -s sample-data/sample.yml -d sample-data/pandas-sample.pkl -h 127.0.0.1 -p 6379 -p supersecret
 ```
 
 ### Support
@@ -88,7 +89,7 @@ Install the Python requirements listed in `requirements.txt`.
 ```bash
 git clone https://github.com/RedisVentures/data-loader.git
 cd redisvl
-pip install .
+pip install -e .
 ```
 
 ### Creating Input Data

redisvl/index.py

@@ -84,5 +84,6 @@ async def create(
             definition=IndexDefinition(prefix=[self.prefix], index_type=storage_type),
         )
 
-    async def delete(self):
-        await self.redis_conn.ft(self.index_name).dropindex(delete_documents=True)
+    async def delete(self, dd: bool = True):
+        # Delete the search index
+        await self.redis_conn.ft(self.index_name).dropindex(delete_documents=dd)

redisvl/query.py

@@ -9,7 +9,7 @@ def create_vector_query(
     number_of_results: int = 20,
     vector_field_name: str = "vector",
     tags: str = "*",
-):
+) -> Query:
     base_query = f"{tags}=>[{search_type} {number_of_results} @{vector_field_name} $vector AS vector_score]"
     return (
         Query(base_query)

redisvl/schema.py

@@ -88,7 +88,7 @@ def _create_vector_field(
     algorithm: str = "FLAT",
     datatype: str = "FLOAT32",
     distance_metric: str = "COSINE",
-    initial_cap: int = 1000000,
+    initial_cap: int = 20000,
     block_size: int = 1000,
     m: int = 16,
     ef_construction: int = 200,

sample-data/sample.yml

@@ -14,6 +14,7 @@ fields:
       separator: "|"
   vector:
     vector:
+      initial_cap: 20000
       datatype: "float32"
       algorithm: "flat"
       dims: 768