Perform Hybrid Vector and Full-Text Search

Connect to your cluster using MongoDB Compass.

Open Compass and connect to your cluster. For detailed instructions, see Connect to a Cluster via Compass.

Specify the database and collection.

On the Database screen, click the name of the database, then click the name of the collection.

Create the MongoDB Vector Search index.

1. In the Indexes tab, then select Search Indexes.

2. From the Create dropdown, select Search Index.

3. In the Name of Search Index field, enter hybrid-vector-search.

   Your MongoDB Vector Search index is named vector_index by default. If you use this name, then your index will be the default MongoDB Vector Search index for any MongoDB Vector Search query that does not specify a different index name in the pipeline. If you are creating multiple indexes, we recommend that you maintain a consistent, descriptive naming convention across your indexes.

4. Under Vector Search, specify the JSON MongoDB Vector Search index definition.

   1
   {
   2
     "fields": [{
   3
       "type": "vector",
   4
       "path": "plot_embedding_voyage_4_large",
   5
       "numDimensions": 2048,
   6
       "similarity": "dotProduct"
   7
     }]
   8
   }

5. Click Create Search Index.

Create the MongoDB Search index.

1. In the Indexes tab, then select Search Indexes.

2. From the Create dropdown, select Search Index.

3. In the Name of Search Index field, enter hybrid-full-text-search.

   Your MongoDB Search index is named default by default. If you keep this name, then your index will be the default Search index for any MongoDB Search query that does not specify a different index option in its operators. If you are creating multiple indexes, we recommend that you maintain a consistent, descriptive naming convention across your indexes.

4. Under Search, specify the JSON MongoDB Vector Search index definition.

   1
   {
   2
     "mappings": {
   3
       "dynamic": true
   4
     }
   5
   }

5. Click Create Search Index.

Connect to the cluster using mongosh.

To learn more, see Connect to a Cluster via mongosh.

Switch to the database that contains the collection for which you want to create the index.

use sample_mflix

switched to db sample_mflix

Define the MongoDB Vector Search index.

Run the following command. This index definition indexes the plot_embedding_voyage_4_large field as the MongoDB Vector Search field when querying the collection.

1
db.embedded_movies.createSearchIndex(
2
  "hybrid-vector-search", 
3
  "vectorSearch", 
4
  {
5
    "fields": [
6
      {
7
        "type": "vector",
8
        "path": "plot_embedding_voyage_4_large",
9
        "numDimensions": 2048,
10
        "similarity": "dotProduct"
11
      }
12
    ]
13
  }
14
);

Define the MongoDB Search index.

The following index definition automatically indexes all the dynamically indexable fields in the collection.

1
db.embedded_movies.createSearchIndex(
2
  "hybrid-full-text-search", 
3
  "search", 
4
  {
5
    "mappings": {
6
      "dynamic": true
7
    }
8
  }
9
);

Initialize your Node.js project.

# Create a new directory and initialize the project
mkdir atlas-search-project && cd atlas-search-project
npm init -y
# Add the MongoDB Node.js Driver to your project
npm install mongodb

For detailed installation instructions, see the MongoDB Node Driver documentation.

Define the MongoDB Vector Search index.

The following index definition indexes the plot_embedding_voyage_4_large field as the MongoDB Vector Search field when querying the collection.

1. Create a file named vector-search-index.js, and paste the following code into it:

   vector-search-index.js

   1
   const { MongoClient } = require("mongodb");
   2
   3
   // Connect to your MongoDB deployment
   4
   const MONGODB_URI = "<connection-string>";
   5
   const client = new MongoClient(MONGODB_URI);
   6
   7
   async function run() {
   8
       try {
   9
         const database = client.db("sample_mflix");
   10
         const collection = database.collection("embedded_movies");
   11
   12
         // Define your vector search index
   13
         const index = {
   14
             name: "hybrid-vector-search",
   15
             type: "vectorSearch",
   16
             definition: {
   17
               "fields": [
   18
                 {
   19
                   "type": "vector",
   20
                   "numDimensions": 2048,
   21
                   "path": "plot_embedding_voyage_4_large",
   22
                   "similarity": "dotProduct"
   23
                 }
   24
               ]
   25
             }
   26
         }
   27
   28
         // Call the method to create the index
   29
         const result = await collection.createSearchIndex(index);
   30
         console.log(result);
   31
       } finally {
   32
         await client.close();
   33
       }
   34
   }
   35
   run().catch(console.dir);

2. Run the following command to execute the code:

   node vector-search-index.js

   Hide output

   hybrid-vector-search

   MongoDB Vector Search might take few minutes to create the index.

Define the MongoDB Search index.

The following index definition automatically indexes all dynamically indexable field types in the collection.

1. Create a file named text-search-index.js, and paste the following code into it:

   text-search-index.js

   1
   const { MongoClient } = require("mongodb");
   2
   3
   // Connect to your MongoDB deployment
   4
   const MONGODB_URI = "<connection-string>";
   5
   const client = new MongoClient(MONGODB_URI);
   6
   7
   async function run() {
   8
       try {
   9
         const database = client.db("sample_mflix");
   10
         const collection = database.collection("embedded_movies");
   11
   12
         // Define your search index
   13
         const index = {
   14
             name: "hybrid-full-text-search",
   15
             type: "search",
   16
             definition: {
   17
               "mappings": {
   18
                 "dynamic": true
   19
               }
   20
             }
   21
         }
   22
   23
         // Call the method to create the index
   24
         const result = await collection.createSearchIndex(index);
   25
         console.log(result);
   26
       } finally {
   27
         await client.close();
   28
       }
   29
   }
   30
   run().catch(console.dir);

2. Run the following command to execute the code:

   node text-search-index.js

   Hide output

   hybrid-full-text-search

   MongoDB Search might take few minutes to create the index.

Set up the Python project.

# Create a new directory for the project
mkdir atlas-search-project && cd atlas-search-project
# Install PyMongo
pip install pymongo

For detailed installation instructions, see MongoDB Python Driver (PyMongo).

Define the MongoDB Vector Search index.

Create a create_vector_index.py file in your project directory, and copy and paste the following code into the file.

1
from pymongo.mongo_client import MongoClient
2
from pymongo.operations import SearchIndexModel
3
import time
4
5
# Connect to your Atlas deployment
6
uri = "<connection-string>"
7
client = MongoClient(uri)
8
9
# Access your database and collection
10
database = client["sample_mflix"]
11
collection = database["embedded_movies"]
12
13
# Define your index
14
search_index_model = SearchIndexModel(
15
  definition={
16
    "fields": [
17
      {
18
        "type": "vector",
19
        "path": "plot_embedding_voyage_4_large",
20
        "numDimensions": 2048,
21
        "similarity": "dotProduct"
22
      }
23
    ]
24
  },
25
  name="hybrid-vector-search",
26
  type="vectorSearch"
27
)
28
29
# Create the index
30
result = collection.create_search_index(model=search_index_model)
31
print("New search index named " + result + " is building.")
32
33
# Wait for initial sync to complete
34
print("Polling to check if the index is ready. This may take up to a minute.")
35
predicate=None
36
if predicate is None:
37
  predicate = lambda index: index.get("queryable") is True
38
39
while True:
40
  indices = list(collection.list_search_indexes(result))
41
  if len(indices) and predicate(indices[0]):
42
    break
43
  time.sleep(5)
44
print(result + " is ready for querying.")
45
46
client.close()

Replace <connection-string> with the connection string for your Atlas cluster or local Atlas deployment.

mongodb+srv://<db_username>:<db_password>@<clusterName>.<hostname>.mongodb.net

mongodb://localhost:<port-number>/?directConnection=true

Create the MongoDB Vector Search index.

python create_vector_index.py

New search index named hybrid-vector-search is building.
Polling to check if the index is ready. This may take up to a minute.
hybrid-vector-search is ready for querying.

Define the MongoDB Vector Search index.

Create a create_search_index.py file in your project directory, and copy and paste the following code into the file.

1
from pymongo.mongo_client import MongoClient
2
from pymongo.operations import SearchIndexModel
3
import time
4
5
# Connect to your Atlas deployment
6
uri = "<connection-string>"
7
client = MongoClient(uri)
8
9
# Access your database and collection
10
database = client["sample_mflix"]
11
collection = database["embedded_movies"]
12
13
# Define your index 
14
search_index_model = SearchIndexModel(
15
    definition={
16
        "mappings": {
17
            "dynamic": True,
18
        },
19
    },
20
    name="hybrid-full-text-search",
21
)
22
23
# Create the index
24
result = collection.create_search_index(model=search_index_model)
25
print("New search index named " + result + " is building.")
26
27
# Wait for initial sync to complete
28
print("Polling to check if the index is ready. This may take up to a minute.")
29
predicate=None
30
if predicate is None:
31
  predicate = lambda index: index.get("queryable") is True
32
33
while True:
34
  indices = list(collection.list_search_indexes(result))
35
  if len(indices) and predicate(indices[0]):
36
    break
37
  time.sleep(5)
38
print(result + " is ready for querying.")
39
40
client.close()

Replace <connection-string> with the connection string for your Atlas cluster or local Atlas deployment.

mongodb+srv://<db_username>:<db_password>@<clusterName>.<hostname>.mongodb.net

mongodb://localhost:<port-number>/?directConnection=true

Create the MongoDB Vector Search index.

python create_search_index.py

New search index named hybrid-full-text-search is building.
Polling to check if the index is ready. This may take up to a minute.
hybrid-full-text-search is ready for querying.

Connect to your cluster using MongoDB Compass.

Open Compass and connect to your cluster. For detailed instructions, see Connect to a Cluster via Compass.

Specify the database and collection.

On the Database screen, click the name of the database, then click the name of the collection.

Create the MongoDB Vector Search index.

1. In the Indexes tab, then select Search Indexes.

2. From the Create dropdown, select Search Index.

3. In the Name of Search Index field, enter hybrid-vector-search.

   Your MongoDB Vector Search index is named vector_index by default. If you use this name, then your index will be the default MongoDB Vector Search index for any MongoDB Vector Search query that does not specify a different index name in the pipeline. If you are creating multiple indexes, we recommend that you maintain a consistent, descriptive naming convention across your indexes.

4. Under Vector Search, specify the JSON MongoDB Vector Search index definition.

   1
   {
   2
     "fields": [{
   3
       "type": "vector",
   4
       "path": "plot_embedding_voyage_4_large",
   5
       "numDimensions": 2048,
   6
       "similarity": "dotProduct"
   7
     }]
   8
   }

5. Click Create Search Index.

Create the MongoDB Search index.

1. In the Indexes tab, then select Search Indexes.

2. From the Create dropdown, select Search Index.

3. In the Name of Search Index field, enter hybrid-full-text-search.

   Your MongoDB Search index is named default by default. If you keep this name, then your index will be the default Search index for any MongoDB Search query that does not specify a different index option in its operators. If you are creating multiple indexes, we recommend that you maintain a consistent, descriptive naming convention across your indexes.

4. Under Search, specify the JSON MongoDB Vector Search index definition.

   1
   {
   2
     "mappings": {
   3
       "dynamic": true
   4
     }
   5
   }

5. Click Create Search Index.

Connect to the cluster using mongosh.

To learn more, see Connect to a Cluster via mongosh.

Switch to the database that contains the collection for which you want to create the index.

use sample_mflix

switched to db sample_mflix

Define the MongoDB Vector Search index.

Run the following command. This index definition indexes the plot_embedding_voyage_4_large field as the MongoDB Vector Search field when querying the collection.

1
db.embedded_movies.createSearchIndex(
2
  "hybrid-vector-search", 
3
  "vectorSearch", 
4
  {
5
    "fields": [
6
      {
7
        "type": "vector",
8
        "path": "plot_embedding_voyage_4_large",
9
        "numDimensions": 2048,
10
        "similarity": "dotProduct"
11
      }
12
    ]
13
  }
14
);

Define the MongoDB Search index.

The following index definition automatically indexes all the dynamically indexable fields in the collection.

1
db.embedded_movies.createSearchIndex(
2
  "hybrid-full-text-search", 
3
  "search", 
4
  {
5
    "mappings": {
6
      "dynamic": true
7
    }
8
  }
9
);

Initialize your Node.js project.

# Create a new directory and initialize the project
mkdir atlas-search-project && cd atlas-search-project
npm init -y
# Add the MongoDB Node.js Driver to your project
npm install mongodb

For detailed installation instructions, see the MongoDB Node Driver documentation.

Define the MongoDB Vector Search index.

The following index definition indexes the plot_embedding_voyage_4_large field as the MongoDB Vector Search field when querying the collection.

1. Create a file named vector-search-index.js, and paste the following code into it:

   vector-search-index.js

   1
   const { MongoClient } = require("mongodb");
   2
   3
   // Connect to your MongoDB deployment
   4
   const MONGODB_URI = "<connection-string>";
   5
   const client = new MongoClient(MONGODB_URI);
   6
   7
   async function run() {
   8
       try {
   9
         const database = client.db("sample_mflix");
   10
         const collection = database.collection("embedded_movies");
   11
   12
         // Define your vector search index
   13
         const index = {
   14
             name: "hybrid-vector-search",
   15
             type: "vectorSearch",
   16
             definition: {
   17
               "fields": [
   18
                 {
   19
                   "type": "vector",
   20
                   "numDimensions": 2048,
   21
                   "path": "plot_embedding_voyage_4_large",
   22
                   "similarity": "dotProduct"
   23
                 }
   24
               ]
   25
             }
   26
         }
   27
   28
         // Call the method to create the index
   29
         const result = await collection.createSearchIndex(index);
   30
         console.log(result);
   31
       } finally {
   32
         await client.close();
   33
       }
   34
   }
   35
   run().catch(console.dir);

2. Run the following command to execute the code:

   node vector-search-index.js

   Hide output

   hybrid-vector-search

   MongoDB Vector Search might take few minutes to create the index.

Define the MongoDB Search index.

The following index definition automatically indexes all dynamically indexable field types in the collection.

1. Create a file named text-search-index.js, and paste the following code into it:

   text-search-index.js

   1
   const { MongoClient } = require("mongodb");
   2
   3
   // Connect to your MongoDB deployment
   4
   const MONGODB_URI = "<connection-string>";
   5
   const client = new MongoClient(MONGODB_URI);
   6
   7
   async function run() {
   8
       try {
   9
         const database = client.db("sample_mflix");
   10
         const collection = database.collection("embedded_movies");
   11
   12
         // Define your search index
   13
         const index = {
   14
             name: "hybrid-full-text-search",
   15
             type: "search",
   16
             definition: {
   17
               "mappings": {
   18
                 "dynamic": true
   19
               }
   20
             }
   21
         }
   22
   23
         // Call the method to create the index
   24
         const result = await collection.createSearchIndex(index);
   25
         console.log(result);
   26
       } finally {
   27
         await client.close();
   28
       }
   29
   }
   30
   run().catch(console.dir);

2. Run the following command to execute the code:

   node text-search-index.js

   Hide output

   hybrid-full-text-search

   MongoDB Search might take few minutes to create the index.

Set up the Python project.

# Create a new directory for the project
mkdir atlas-search-project && cd atlas-search-project
# Install PyMongo
pip install pymongo

For detailed installation instructions, see MongoDB Python Driver (PyMongo).

Define the MongoDB Vector Search index.

Create a create_vector_index.py file in your project directory, and copy and paste the following code into the file.

1
from pymongo.mongo_client import MongoClient
2
from pymongo.operations import SearchIndexModel
3
import time
4
5
# Connect to your Atlas deployment
6
uri = "<connection-string>"
7
client = MongoClient(uri)
8
9
# Access your database and collection
10
database = client["sample_mflix"]
11
collection = database["embedded_movies"]
12
13
# Define your index
14
search_index_model = SearchIndexModel(
15
  definition={
16
    "fields": [
17
      {
18
        "type": "vector",
19
        "path": "plot_embedding_voyage_4_large",
20
        "numDimensions": 2048,
21
        "similarity": "dotProduct"
22
      }
23
    ]
24
  },
25
  name="hybrid-vector-search",
26
  type="vectorSearch"
27
)
28
29
# Create the index
30
result = collection.create_search_index(model=search_index_model)
31
print("New search index named " + result + " is building.")
32
33
# Wait for initial sync to complete
34
print("Polling to check if the index is ready. This may take up to a minute.")
35
predicate=None
36
if predicate is None:
37
  predicate = lambda index: index.get("queryable") is True
38
39
while True:
40
  indices = list(collection.list_search_indexes(result))
41
  if len(indices) and predicate(indices[0]):
42
    break
43
  time.sleep(5)
44
print(result + " is ready for querying.")
45
46
client.close()

Replace <connection-string> with the connection string for your Atlas cluster or local Atlas deployment.

mongodb+srv://<db_username>:<db_password>@<clusterName>.<hostname>.mongodb.net

mongodb://localhost:<port-number>/?directConnection=true

Create the MongoDB Vector Search index.

python create_vector_index.py

New search index named hybrid-vector-search is building.
Polling to check if the index is ready. This may take up to a minute.
hybrid-vector-search is ready for querying.

Define the MongoDB Vector Search index.

Create a create_search_index.py file in your project directory, and copy and paste the following code into the file.

1
from pymongo.mongo_client import MongoClient
2
from pymongo.operations import SearchIndexModel
3
import time
4
5
# Connect to your Atlas deployment
6
uri = "<connection-string>"
7
client = MongoClient(uri)
8
9
# Access your database and collection
10
database = client["sample_mflix"]
11
collection = database["embedded_movies"]
12
13
# Define your index 
14
search_index_model = SearchIndexModel(
15
    definition={
16
        "mappings": {
17
            "dynamic": True,
18
        },
19
    },
20
    name="hybrid-full-text-search",
21
)
22
23
# Create the index
24
result = collection.create_search_index(model=search_index_model)
25
print("New search index named " + result + " is building.")
26
27
# Wait for initial sync to complete
28
print("Polling to check if the index is ready. This may take up to a minute.")
29
predicate=None
30
if predicate is None:
31
  predicate = lambda index: index.get("queryable") is True
32
33
while True:
34
  indices = list(collection.list_search_indexes(result))
35
  if len(indices) and predicate(indices[0]):
36
    break
37
  time.sleep(5)
38
print(result + " is ready for querying.")
39
40
client.close()

Replace <connection-string> with the connection string for your Atlas cluster or local Atlas deployment.

mongodb+srv://<db_username>:<db_password>@<clusterName>.<hostname>.mongodb.net

mongodb://localhost:<port-number>/?directConnection=true

Create the MongoDB Vector Search index.

python create_search_index.py

New search index named hybrid-full-text-search is building.
Polling to check if the index is ready. This may take up to a minute.
hybrid-full-text-search is ready for querying.

Connect to your cluster using MongoDB Compass.

Open Compass and connect to your cluster. For detailed instructions, see Connect to a Cluster via Compass.

Specify the database and collection.

On the Database screen, click the name of the database, then click the name of the collection.

Create the MongoDB Vector Search index.

1. In the Indexes tab, then select Search Indexes.

2. From the Create dropdown, select Search Index.

3. In the Name of Search Index field, enter hybrid-vector-search.

4. Under Vector Search, specify the JSON MongoDB Vector Search index definition.

   1
   {
   2
     "fields": [
   3
       {
   4
         "type": "autoEmbed",
   5
         "modality": "text",
   6
         "path": "fullplot",
   7
         "model": "voyage-4"
   8
       }
   9
     ]
   10
   }

   This index definition indexes the fullplot field as the autoEmbed field, for which MongoDB Vector Search automatically generates embeddings using the voyage-4 embedding model.

5. Click Create Search Index.

Create the MongoDB Search index.

1. In the Indexes tab, then select Search Indexes.

2. From the Create dropdown, select Search Index.

3. In the Name of Search Index field, enter hybrid-full-text-search.

   Your MongoDB Search index is named default by default. If you keep this name, then your index will be the default Search index for any MongoDB Search query that does not specify a different index option in its operators. If you are creating multiple indexes, we recommend that you maintain a consistent, descriptive naming convention across your indexes.

4. Under Search, specify the JSON MongoDB Vector Search index definition.

   1
   {
   2
     "mappings": {
   3
       "dynamic": true
   4
     }
   5
   }

5. Click Create Search Index.

Connect to the cluster using mongosh.

To learn more, see Connect to a Cluster via mongosh.

Switch to the database that contains the collection for which you want to create the index.

use sample_mflix

switched to db sample_mflix

Define the MongoDB Vector Search index.

Run the following command. This index definition indexes the fullplot field as the MongoDB Vector Search field, for which MongoDB Vector Search automatically generates embeddings using the voyage-4 embedding model.

1
db.embedded_movies.createSearchIndex(
2
  "hybrid-vector-search", 
3
  "vectorSearch", 
4
  {
5
    "fields": [
6
      {
7
        "type": "autoEmbed",
8
        "modality": "text",
9
        "path": "fullplot",
10
        "model": "voyage-4"
11
      }
12
    ]
13
  }
14
);

Define the MongoDB Search index.

The following index definition automatically indexes all the dynamically indexable fields in the collection.

1
db.embedded_movies.createSearchIndex(
2
  "hybrid-full-text-search", 
3
  "search", 
4
  {
5
    "mappings": {
6
      "dynamic": true
7
    }
8
  }
9
);

Initialize your Node.js project.

# Create a new directory and initialize the project
mkdir atlas-search-project && cd atlas-search-project
npm init -y
# Add the MongoDB Node.js Driver to your project
npm install mongodb

For detailed installation instructions, see the MongoDB Node Driver documentation.

Define the MongoDB Vector Search index.

The following index definition indexes the fullplot field as the autoEmbed type field, for which MongoDB Vector Search automatically generates embeddings using the voyage-4 embedding model.

1. Create a file named vector-search-index.js, and paste the following code into it:

   vector-search-index.js

   1
   const { MongoClient } = require("mongodb");
   2
   3
   // Connect to your MongoDB deployment
   4
   const MONGODB_URI = "<connection-string>";
   5
   const client = new MongoClient(MONGODB_URI);
   6
   7
   async function run() {
   8
       try {
   9
         const database = client.db("sample_mflix");
   10
         const collection = database.collection("embedded_movies");
   11
   12
         // Define your vector search index
   13
         const index = {
   14
             name: "hybrid-vector-search",
   15
             type: "vectorSearch",
   16
             definition: {
   17
               "fields": [
   18
                 {
   19
                   "type": "autoEmbed",
   20
                   "modality": "text",
   21
                   "path": "fullplot",
   22
                   "model": "voyage-4"
   23
                 }
   24
               ]
   25
             }
   26
         }
   27
   28
         // Call the method to create the index
   29
         const result = await collection.createSearchIndex(index);
   30
         console.log(result);
   31
       } finally {
   32
         await client.close();
   33
       }
   34
   }
   35
   run().catch(console.dir);

2. Run the following command to execute the code:

   node vector-search-index.js

   Hide output

   hybrid-vector-search

   MongoDB Vector Search might take few minutes to create the index.

Define the MongoDB Search index.

The following index definition automatically indexes all dynamically indexable field types in the collection.

1. Create a file named text-search-index.js, and paste the following code into it:

   text-search-index.js

   1
   const { MongoClient } = require("mongodb");
   2
   3
   // Connect to your MongoDB deployment
   4
   const MONGODB_URI = "<connection-string>";
   5
   const client = new MongoClient(MONGODB_URI);
   6
   7
   async function run() {
   8
       try {
   9
         const database = client.db("sample_mflix");
   10
         const collection = database.collection("embedded_movies");
   11
   12
         // Define your search index
   13
         const index = {
   14
             name: "hybrid-full-text-search",
   15
             type: "search",
   16
             definition: {
   17
               "mappings": {
   18
                 "dynamic": true
   19
               }
   20
             }
   21
         }
   22
   23
         // Call the method to create the index
   24
         const result = await collection.createSearchIndex(index);
   25
         console.log(result);
   26
       } finally {
   27
         await client.close();
   28
       }
   29
   }
   30
   run().catch(console.dir);

   This index definition indexes the fullplot field as the autoEmbed field, for which MongoDB Vector Search automatically generates embeddings using the voyage-4 embedding model.

2. Run the following command to execute the code:

   node text-search-index.js

   Hide output

   hybrid-full-text-search

   MongoDB Search might take few minutes to create the index.

Set up the Python project.

# Create a new directory for the project
mkdir atlas-search-project && cd atlas-search-project
# Install PyMongo
pip install pymongo

For detailed installation instructions, see MongoDB Python Driver (PyMongo).

Define the MongoDB Vector Search index.

Create a create_vector_index.py file in your project directory, and copy and paste the following code into the file.

1
from pymongo.mongo_client import MongoClient
2
from pymongo.operations import SearchIndexModel
3
import time
4
5
# Connect to your Atlas deployment
6
uri = "<connection-string>"
7
client = MongoClient(uri)
8
9
# Access your database and collection
10
database = client["sample_mflix"]
11
collection = database["embedded_movies"]
12
13
# Define your index
14
search_index_model = SearchIndexModel(
15
  definition={
16
    "fields": [
17
      {
18
        "type": "autoEmbed",
19
        "modality": "text",
20
        "path": "fullplot",
21
        "model": "voyage-4"
22
      }
23
    ]
24
  },
25
  name="hybrid-vector-search",
26
  type="vectorSearch"
27
)
28
29
# Create the index
30
result = collection.create_search_index(model=search_index_model)
31
print("New search index named " + result + " is building.")
32
33
# Wait for initial sync to complete
34
print("Polling to check if the index is ready. This may take up to a minute.")
35
predicate=None
36
if predicate is None:
37
  predicate = lambda index: index.get("queryable") is True
38
39
while True:
40
  indices = list(collection.list_search_indexes(result))
41
  if len(indices) and predicate(indices[0]):
42
    break
43
  time.sleep(5)
44
print(result + " is ready for querying.")
45
46
client.close()

Replace <connection-string> with the connection string for your Atlas cluster or local Atlas deployment.

mongodb+srv://<db_username>:<db_password>@<clusterName>.<hostname>.mongodb.net

mongodb://localhost:<port-number>/?directConnection=true

Create the MongoDB Vector Search index.

python create_vector_index.py

New search index named hybrid-vector-search is building.
Polling to check if the index is ready. This may take up to a minute.
hybrid-vector-search is ready for querying.

Define the MongoDB Vector Search index.

Create a create_search_index.py file in your project directory, and copy and paste the following code into the file.

1
from pymongo.mongo_client import MongoClient
2
from pymongo.operations import SearchIndexModel
3
import time
4
5
# Connect to your Atlas deployment
6
uri = "<connection-string>"
7
client = MongoClient(uri)
8
9
# Access your database and collection
10
database = client["sample_mflix"]
11
collection = database["embedded_movies"]
12
13
# Define your index 
14
search_index_model = SearchIndexModel(
15
    definition={
16
        "mappings": {
17
            "dynamic": True,
18
        },
19
    },
20
    name="hybrid-full-text-search",
21
)
22
23
# Create the index
24
result = collection.create_search_index(model=search_index_model)
25
print("New search index named " + result + " is building.")
26
27
# Wait for initial sync to complete
28
print("Polling to check if the index is ready. This may take up to a minute.")
29
predicate=None
30
if predicate is None:
31
  predicate = lambda index: index.get("queryable") is True
32
33
while True:
34
  indices = list(collection.list_search_indexes(result))
35
  if len(indices) and predicate(indices[0]):
36
    break
37
  time.sleep(5)
38
print(result + " is ready for querying.")
39
40
client.close()

This index definition indexes the fullplot field as the autoEmbed field, for which MongoDB Vector Search automatically generates embeddings using the voyage-4 embedding model.

Replace <connection-string> with the connection string for your Atlas cluster or local Atlas deployment.

mongodb+srv://<db_username>:<db_password>@<clusterName>.<hostname>.mongodb.net

mongodb://localhost:<port-number>/?directConnection=true

Create the MongoDB Vector Search index.

python create_search_index.py

New search index named hybrid-full-text-search is building.
Polling to check if the index is ready. This may take up to a minute.
hybrid-full-text-search is ready for querying.

Connect to your cluster using MongoDB Compass.

Open Compass and connect to your cluster. For detailed instructions, see Connect to a Cluster via Compass.

Specify the database and collection.

On the Database screen, click the name of the database, then click the name of the collection.

Create the MongoDB Vector Search index.

1. In the Indexes tab, then select Search Indexes.

2. From the Create dropdown, select Search Index.

3. In the Name of Search Index field, enter hybrid-vector-search.

4. Under Vector Search, specify the JSON MongoDB Vector Search index definition.

   1
   {
   2
     "fields": [
   3
       {
   4
         "type": "autoEmbed",
   5
         "modality": "text",
   6
         "path": "fullplot",
   7
         "model": "voyage-4"
   8
       }
   9
     ]
   10
   }

   This index definition indexes the fullplot field as the autoEmbed field, for which MongoDB Vector Search automatically generates embeddings using the voyage-4 embedding model.

5. Click Create Search Index.

Create the MongoDB Search index.

1. In the Indexes tab, then select Search Indexes.

2. From the Create dropdown, select Search Index.

3. In the Name of Search Index field, enter hybrid-full-text-search.

   Your MongoDB Search index is named default by default. If you keep this name, then your index will be the default Search index for any MongoDB Search query that does not specify a different index option in its operators. If you are creating multiple indexes, we recommend that you maintain a consistent, descriptive naming convention across your indexes.

4. Under Search, specify the JSON MongoDB Vector Search index definition.

   1
   {
   2
     "mappings": {
   3
       "dynamic": true
   4
     }
   5
   }

5. Click Create Search Index.

Connect to the cluster using mongosh.

To learn more, see Connect to a Cluster via mongosh.

Switch to the database that contains the collection for which you want to create the index.

use sample_mflix

switched to db sample_mflix

Define the MongoDB Vector Search index.

Run the following command. This index definition indexes the fullplot field as the MongoDB Vector Search field, for which MongoDB Vector Search automatically generates embeddings using the voyage-4 embedding model.

1
db.embedded_movies.createSearchIndex(
2
  "hybrid-vector-search", 
3
  "vectorSearch", 
4
  {
5
    "fields": [
6
      {
7
        "type": "autoEmbed",
8
        "modality": "text",
9
        "path": "fullplot",
10
        "model": "voyage-4"
11
      }
12
    ]
13
  }
14
);

Define the MongoDB Search index.

The following index definition automatically indexes all the dynamically indexable fields in the collection.

1
db.embedded_movies.createSearchIndex(
2
  "hybrid-full-text-search", 
3
  "search", 
4
  {
5
    "mappings": {
6
      "dynamic": true
7
    }
8
  }
9
);

Initialize your Node.js project.

# Create a new directory and initialize the project
mkdir atlas-search-project && cd atlas-search-project
npm init -y
# Add the MongoDB Node.js Driver to your project
npm install mongodb

For detailed installation instructions, see the MongoDB Node Driver documentation.

Define the MongoDB Vector Search index.

The following index definition indexes the fullplot field as the autoEmbed type field, for which MongoDB Vector Search automatically generates embeddings using the voyage-4 embedding model.

1. Create a file named vector-search-index.js, and paste the following code into it:

   vector-search-index.js

   1
   const { MongoClient } = require("mongodb");
   2
   3
   // Connect to your MongoDB deployment
   4
   const MONGODB_URI = "<connection-string>";
   5
   const client = new MongoClient(MONGODB_URI);
   6
   7
   async function run() {
   8
       try {
   9
         const database = client.db("sample_mflix");
   10
         const collection = database.collection("embedded_movies");
   11
   12
         // Define your vector search index
   13
         const index = {
   14
             name: "hybrid-vector-search",
   15
             type: "vectorSearch",
   16
             definition: {
   17
               "fields": [
   18
                 {
   19
                   "type": "autoEmbed",
   20
                   "modality": "text",
   21
                   "path": "fullplot",
   22
                   "model": "voyage-4"
   23
                 }
   24
               ]
   25
             }
   26
         }
   27
   28
         // Call the method to create the index
   29
         const result = await collection.createSearchIndex(index);
   30
         console.log(result);
   31
       } finally {
   32
         await client.close();
   33
       }
   34
   }
   35
   run().catch(console.dir);

2. Run the following command to execute the code:

   node vector-search-index.js

   Hide output

   hybrid-vector-search

   MongoDB Vector Search might take few minutes to create the index.

Define the MongoDB Search index.

The following index definition automatically indexes all dynamically indexable field types in the collection.

1. Create a file named text-search-index.js, and paste the following code into it:

   text-search-index.js

   1
   const { MongoClient } = require("mongodb");
   2
   3
   // Connect to your MongoDB deployment
   4
   const MONGODB_URI = "<connection-string>";
   5
   const client = new MongoClient(MONGODB_URI);
   6
   7
   async function run() {
   8
       try {
   9
         const database = client.db("sample_mflix");
   10
         const collection = database.collection("embedded_movies");
   11
   12
         // Define your search index
   13
         const index = {
   14
             name: "hybrid-full-text-search",
   15
             type: "search",
   16
             definition: {
   17
               "mappings": {
   18
                 "dynamic": true
   19
               }
   20
             }
   21
         }
   22
   23
         // Call the method to create the index
   24
         const result = await collection.createSearchIndex(index);
   25
         console.log(result);
   26
       } finally {
   27
         await client.close();
   28
       }
   29
   }
   30
   run().catch(console.dir);

   This index definition indexes the fullplot field as the autoEmbed field, for which MongoDB Vector Search automatically generates embeddings using the voyage-4 embedding model.

2. Run the following command to execute the code:

   node text-search-index.js

   Hide output

   hybrid-full-text-search

   MongoDB Search might take few minutes to create the index.

Set up the Python project.

# Create a new directory for the project
mkdir atlas-search-project && cd atlas-search-project
# Install PyMongo
pip install pymongo

For detailed installation instructions, see MongoDB Python Driver (PyMongo).

Define the MongoDB Vector Search index.

Create a create_vector_index.py file in your project directory, and copy and paste the following code into the file.

1
from pymongo.mongo_client import MongoClient
2
from pymongo.operations import SearchIndexModel
3
import time
4
5
# Connect to your Atlas deployment
6
uri = "<connection-string>"
7
client = MongoClient(uri)
8
9
# Access your database and collection
10
database = client["sample_mflix"]
11
collection = database["embedded_movies"]
12
13
# Define your index
14
search_index_model = SearchIndexModel(
15
  definition={
16
    "fields": [
17
      {
18
        "type": "autoEmbed",
19
        "modality": "text",
20
        "path": "fullplot",
21
        "model": "voyage-4"
22
      }
23
    ]
24
  },
25
  name="hybrid-vector-search",
26
  type="vectorSearch"
27
)
28
29
# Create the index
30
result = collection.create_search_index(model=search_index_model)
31
print("New search index named " + result + " is building.")
32
33
# Wait for initial sync to complete
34
print("Polling to check if the index is ready. This may take up to a minute.")
35
predicate=None
36
if predicate is None:
37
  predicate = lambda index: index.get("queryable") is True
38
39
while True:
40
  indices = list(collection.list_search_indexes(result))
41
  if len(indices) and predicate(indices[0]):
42
    break
43
  time.sleep(5)
44
print(result + " is ready for querying.")
45
46
client.close()

Replace <connection-string> with the connection string for your Atlas cluster or local Atlas deployment.

mongodb+srv://<db_username>:<db_password>@<clusterName>.<hostname>.mongodb.net

mongodb://localhost:<port-number>/?directConnection=true

Create the MongoDB Vector Search index.

python create_vector_index.py

New search index named hybrid-vector-search is building.
Polling to check if the index is ready. This may take up to a minute.
hybrid-vector-search is ready for querying.

Define the MongoDB Vector Search index.

Create a create_search_index.py file in your project directory, and copy and paste the following code into the file.

1
from pymongo.mongo_client import MongoClient
2
from pymongo.operations import SearchIndexModel
3
import time
4
5
# Connect to your Atlas deployment
6
uri = "<connection-string>"
7
client = MongoClient(uri)
8
9
# Access your database and collection
10
database = client["sample_mflix"]
11
collection = database["embedded_movies"]
12
13
# Define your index 
14
search_index_model = SearchIndexModel(
15
    definition={
16
        "mappings": {
17
            "dynamic": True,
18
        },
19
    },
20
    name="hybrid-full-text-search",
21
)
22
23
# Create the index
24
result = collection.create_search_index(model=search_index_model)
25
print("New search index named " + result + " is building.")
26
27
# Wait for initial sync to complete
28
print("Polling to check if the index is ready. This may take up to a minute.")
29
predicate=None
30
if predicate is None:
31
  predicate = lambda index: index.get("queryable") is True
32
33
while True:
34
  indices = list(collection.list_search_indexes(result))
35
  if len(indices) and predicate(indices[0]):
36
    break
37
  time.sleep(5)
38
print(result + " is ready for querying.")
39
40
client.close()

This index definition indexes the fullplot field as the autoEmbed field, for which MongoDB Vector Search automatically generates embeddings using the voyage-4 embedding model.

Replace <connection-string> with the connection string for your Atlas cluster or local Atlas deployment.

mongodb+srv://<db_username>:<db_password>@<clusterName>.<hostname>.mongodb.net

mongodb://localhost:<port-number>/?directConnection=true

Create the MongoDB Vector Search index.

python create_search_index.py

New search index named hybrid-full-text-search is building.
Polling to check if the index is ready. This may take up to a minute.
hybrid-full-text-search is ready for querying.

Navigate to the collection in MongoDB Compass.

On the Database screen, click the sample_mflix database, then click the embedded_movies collection.

Run a basic query.

To run this query in MongoDB Compass:

1. Click the Aggregations tab.

2. Click </> Text to switch to JSON view.

3. Copy and paste to run the following query:

   1
   [
   2
     {
   3
       "$rankFusion": {
   4
         "input": {
   5
           "pipelines": {
   6
             "vectorPipeline": [
   7
               {
   8
                 "$vectorSearch": {
   9
                 "index": "hybrid-vector-search",
   10
                 "path": "plot_embedding_voyage_4_large",
   11
                 "queryVector": [-0.02300029993057251, -0.040718235075473785, 0.026521876454353333, -0.007813499309122562, 0.01958877220749855, -0.032134391367435455, 0.015186801552772522, 0.023990744724869728, -0.0029025499243289232, -0.0019671309273689985, 0.01254561822861433, -0.016287293285131454, -0.029053010046482086, 0.01408630795776844, -0.00891399197280407, 0.01958877220749855, -0.0508427694439888, -0.015737047418951988, 0.012215470895171165, -0.0036316262558102608, 0.0033152345567941666, 0.0033840155228972435, -0.00748335151001811, 0.002737476024776697, 0.03257458657026291, -0.01892847754061222, -0.012050396762788296, 0.02432089112699032, 0.028392715379595757, 0.033454980701208115, 0.005144803784787655, 0.0072632525116205215, 0.0212395116686821, -0.01683754101395607, -0.002751232124865055, 0.030813800171017647, -0.025861581787467003, 0.00748335151001811, -0.0032326977234333754, -0.030813800171017647, 0.006768031045794487, 0.024651039391756058, -0.03565596789121628, -0.02575153298676014, -0.005970173515379429, 0.02575153298676014, -0.08011587709188461, 0.0022284979932010174, -0.03257458657026291, 0.00522734085097909, -0.0028062567580491304, 0.011059952899813652, 0.0061627598479390144, 0.021349560469388962, -0.0061627598479390144, 0.02200985699892044, 0.006988129578530788, -0.006850568111985922, 0.010784829966723919, -0.0035490894224494696, -0.007538375910371542, 0.0023110350593924522, -0.031033897772431374, -0.04291922226548195, -0.03389517962932587, -0.004181872587651014, -0.02024906873703003, 0.003769187955185771, -0.01650739274919033, -0.0031226484570652246, -0.0026686950586736202, 0.03389517962932587, 0.020689265802502632, -0.025531433522701263, 0.02024906873703003, 0.03125399723649025, 0.006602956913411617, -0.01441645622253418, -0.04974227771162987, 0.005887636449187994, -0.013150889426469803, 0.007593400776386261, 0.00352157698944211, -0.014196357689797878, -0.009849410504102707, -0.019698821008205414, -0.01441645622253418, 0.0018708378775045276, -0.007703450042754412, 0.0020771801937371492, -0.03565596789121628, 0.027402272447943687, 0.007593400776386261, 0.005695050582289696, 0.03389517962932587, 0.014196357689797878, -0.002682451391592622, 0.030373603105545044, -0.01061975583434105, -0.017387786880135536, -0.00522734085097909, -0.013205913826823235, 0.007813499309122562, 0.02509123645722866, 0.00304011139087379, -0.04225892573595047, -0.011500149965286255, 0.005887636449187994, 0.0016163488617166877, -0.03477557376027107, 0.04423981159925461, -0.005144803784787655, -0.004401971120387316, -0.028062567114830017, 0.0087489178404212, 0.0029850867576897144, -0.0062177847139537334, -0.012215470895171165, -0.001430640695616603, 0.017277738079428673, -0.007813499309122562, -0.03191429376602173, 0.033454980701208115, 0.018818426877260208, 0.0035766016226261854, -0.030373603105545044, -0.056125134229660034, -0.01815813221037388, 0.0031501606572419405, 0.013756160624325275, -0.03785695508122444, -0.011775272898375988, 0.04908198118209839, 0.031474094837903976, -0.0004126848070882261, 0.027732418850064278, 0.01716768741607666, 0.005640025716274977, -0.013646110892295837, -0.010124534368515015, -0.005007242318242788, -0.02300029993057251, 0.027622370049357414, 0.015737047418951988, -0.03323488309979439, -0.00018312888278160244, -0.010509707033634186, -0.0024898650590330362, -0.014746603555977345, -0.004704606719315052, 0.03191429376602173, 0.02443094179034233, -0.0013756160624325275, -0.0046220701187849045, -0.049962375313043594, -0.01782798394560814, 0.0003920505696441978, -0.01892847754061222, 0.0012311763130128384, 0.041378531605005264, -0.041378531605005264, -0.02090936340391636, -0.010234583169221878, -0.008418770506978035, 0.03477557376027107, 0.009684337303042412, 0.05194326117634773, -0.010344632901251316, -0.047541290521621704, 0.010509707033634186, -0.03477557376027107, -0.023440496996045113, -0.007153203245252371, 0.002737476024776697, 0.020689265802502632, 0.020689265802502632, 0.03301478549838066, 0.012490593828260899, -0.024210842326283455, -0.0216797087341547, 0.005062267184257507, 0.0032877223566174507, -0.02949320711195469, -0.00232479115948081, -0.023990744724869728, 0.04534030333161354, 0.010124534368515015, 0.015516948886215687, 0.04490010812878609, -0.0007084422395564616, -0.04842168465256691, -0.025531433522701263, 0.0216797087341547, -0.010399657301604748, 0.049962375313043594, -0.02024906873703003, 0.03477557376027107, 0.008803942240774632, 0.02057921513915062, -0.01408630795776844, -0.06074720621109009, -0.010014484636485577, 0.034115277230739594, -0.017387786880135536, -0.02410079352557659, -0.01100492849946022, -0.02575153298676014, -0.026521876454353333, -0.03741675615310669, 0.011610199697315693, -0.045560404658317566, 0.0005811977898702025, 0.016067195683717728, 0.008473794907331467, -0.02024906873703003, -0.03961774334311485, 0.00748335151001811, 0.02784246951341629, 0.021349560469388962, 0.02333044819533825, 0.009574287571012974, 0.0006431004730984569, -0.035876065492630005, 0.002022155560553074, 0.019368674606084824, -0.004181872587651014, -0.011335075832903385, -0.02883291244506836, -0.000839125772472471, 0.006713006179779768, -0.00030263554072007537, -0.0025724018923938274, -0.013811185024678707, 0.001843325444497168, -0.013701136223971844, -0.017277738079428673, -0.006245296914130449, -0.006933104712516069, -0.014636554755270481, 0.0033977716229856014, 0.004044311121106148, -0.01584709621965885, 0.00858384370803833, -0.0042093852534890175, 0.0005124169983901083, -0.013315963558852673, -0.03301478549838066, -0.011059952899813652, -0.02057921513915062, 0.0010385900968685746, -0.002421084325760603, 0.00043503858614712954, 0.02443094179034233, 0.009794386103749275, -0.002751232124865055, 0.006382858380675316, 0.018488280475139618, 0.03565596789121628, -0.021789757534861565, 0.011830298230051994, -0.021569659933447838, -0.00034906258224509656, -0.032134391367435455, 0.015406900085508823, -0.02432089112699032, -0.004181872587651014, 0.010509707033634186, 0.020689265802502632, 0.04468001052737236, -0.018048083409667015, -0.00014701895997859538, -0.036536362022161484, 0.02993340604007244, 0.022890251129865646, -0.024210842326283455, 0.02366059646010399, 0.0005777587648481131, 0.011775272898375988, -0.0349956713616848, 0.05458444356918335, 0.004842168651521206, 0.013646110892295837, 0.022780202329158783, -0.006520419847220182, -0.008803942240774632, -0.0035766016226261854, 0.052383460104465485, -0.011940347030758858, 0.0027925006579607725, 0.011280051432549953, 0.029053010046482086, 0.015406900085508823, 0.009959460236132145, -0.0011899078963324428, 0.035876065492630005, -0.001671373494900763, 0.006575444713234901, -0.014306406490504742, 0.001011077780276537, -0.020689265802502632, -0.021129462867975235, -0.004704606719315052, 0.003342746989801526, -0.005832612048834562, -0.0025724018923938274, -0.003769187955185771, -0.005447439383715391, 0.027952518314123154, 0.011830298230051994, 0.03961774334311485, 0.0550246424973011, 0.0031364045571535826, 0.0012311763130128384, -0.002764988224953413, -0.05150306597352028, -0.02608167938888073, 0.015296850353479385, -0.0020634240936487913, -0.03675645962357521, 0.026962075382471085, 0.023770645260810852, -0.011940347030758858, -0.05898641422390938, -0.03785695508122444, -0.003026355290785432, 0.0021322048269212246, 0.02509123645722866, -0.01925862394273281, 0.03961774334311485, 0.02333044819533825, -0.00031123313237912953, 0.06206779554486275, 0.00010102180385729298, -0.01683754101395607, -0.02751232124865055, 0.03851724788546562, 0.0073182773776352406, 0.02641182765364647, -0.042699120938777924, -0.008969016373157501, -0.01287576649338007, 0.018268181011080742, 0.01991892047226429, -0.002916306024417281, 0.032794687896966934, -0.03873734921216965, 0.023550545796751976, -0.03191429376602173, -0.0072632525116205215, 0.0022972787264734507, 0.023440496996045113, -0.01441645622253418, 0.0035766016226261854, 0.016287293285131454, 0.021569659933447838, -0.0004505142569541931, -0.0028062567580491304, -0.004099335987120867, 0.015516948886215687, 0.02024906873703003, 0.004787143785506487, 0.03477557376027107, -0.009244140237569809, 0.026852024719119072, -0.002778744325041771, 0.003741675755009055, 0.015296850353479385, 0.029053010046482086, -0.020139018073678017, 0.006492907647043467, -0.02575153298676014, 0.03983784094452858, 0.0038242125883698463, 0.010344632901251316, -0.012490593828260899, -0.02333044819533825, -0.019808871671557426, -0.04490010812878609, 0.013205913826823235, -0.037636853754520416, 0.00891399197280407, 0.0011555175296962261, 0.022450054064393044, 0.04225892573595047, 0.0018158131279051304, 0.004869680851697922, 0.02949320711195469, 0.01496670302003622, -0.013150889426469803, -0.04776138812303543, -0.020359117537736893, -0.011665224097669125, -0.00464958231896162, -0.016287293285131454, -0.024651039391756058, -0.005887636449187994, -0.0020634240936487913, 0.0014581530122086406, -0.020028969272971153, -0.002861281391233206, 0.0072632525116205215, -0.022890251129865646, -0.027292221784591675, 0.017938032746315002, 0.03125399723649025, -0.012600642628967762, -0.02333044819533825, 0.03477557376027107, -0.027072124183177948, 0.022780202329158783, -0.010509707033634186, 0.02784246951341629, -0.02057921513915062, -0.010949904099106789, -0.011830298230051994, -0.023550545796751976, 0.005364902783185244, 0.02476108819246292, 0.0002820013032760471, 0.0036591386888176203, 0.04423981159925461, 0.022780202329158783, 0.047981489449739456, -0.02200985699892044, 0.009904435835778713, 0.0036316262558102608, -0.007813499309122562, 0.02608167938888073, 0.014306406490504742, 0.011114977300167084, -0.040057938545942307, 0.01782798394560814, -0.022450054064393044, 0.043799616396427155, 0.0212395116686821, -0.022119905799627304, -0.015626998618245125, 0.013811185024678707, 0.026852024719119072, 0.0029025499243289232, -0.01782798394560814, 0.005777587182819843, 0.03851724788546562, -0.047981489449739456, 0.011610199697315693, 0.037636853754520416, 0.01408630795776844, -0.026191730052232742, 0.025311335921287537, 0.04181872680783272, 0.027402272447943687, -0.004512020852416754, -0.044459909200668335, 0.004236897453665733, -0.022229954600334167, -0.005309877917170525, 0.005254853516817093, 0.002517377259209752, 0.016067195683717728, 0.02476108819246292, -0.001341225695796311, -0.001341225695796311, 0.023440496996045113, -0.014746603555977345, 0.00748335151001811, 0.03389517962932587, -0.014031283557415009, -0.04886188358068466, -0.007813499309122562, -0.03389517962932587, 0.034115277230739594, -0.00522734085097909, 0.03807705268263817, -0.013095865026116371, -0.00619027204811573, 0.025641482323408127, 0.023770645260810852, -0.02751232124865055, 0.013315963558852673, 0.030373603105545044, -0.01958877220749855, 0.007923548109829426, -0.016727490350604057, 0.01782798394560814, -0.008693893440067768, -0.01496670302003622, 0.020139018073678017, -0.007703450042754412, -0.010069509036839008, 0.006602956913411617, 0.05216335877776146, 0.022450054064393044, 0.017607884481549263, -0.014526505023241043, -0.020689265802502632, 0.003961774054914713, 0.0020496679935604334, 0.013150889426469803, -0.035215768963098526, -0.024651039391756058, -0.02432089112699032, -0.013811185024678707, 0.031474094837903976, -0.034555476158857346, 0.006933104712516069, 0.038957446813583374, 0.013811185024678707, -0.008803942240774632, -0.02993340604007244, 0.01254561822861433, 0.010894878767430782, -0.011665224097669125, -0.0005674416315741837, -0.02101941406726837, 0.02883291244506836, -0.025201285257935524, 0.0007978572975844145, 0.003934261854737997, -0.004484508186578751, -0.02883291244506836, -0.02883291244506836, 0.0014031283790245652, -0.008803942240774632, -0.01287576649338007, -0.0010661024134606123, 0.025971630588173866, -0.024871138855814934, 0.020799314603209496, 0.010124534368515015, -0.03609616681933403, -0.026191730052232742, -0.015737047418951988, -0.003205185290426016, 0.0174978356808424, 0.03565596789121628, 0.02641182765364647, -0.006547932513058186, -0.00720822811126709, -0.005777587182819843, 0.007098178844898939, 0.03257458657026291, -0.020799314603209496, 0.0073182773776352406, -0.0216797087341547, 0.010949904099106789, -0.0010661024134606123, 0.00522734085097909, 0.011500149965286255, 0.0254213847219944, 0.008473794907331467, 0.01238054409623146, 0.011390101164579391, 0.013811185024678707, 0.0033014784567058086, -0.009684337303042412, -0.00453953305259347, 0.0012999571627005935, 0.008253696374595165, -0.0063553461804986, 0.0035766016226261854, 0.015737047418951988, -0.024540990591049194, 0.016947589814662933, 0.016397343948483467, -0.005144803784787655, 0.013260938227176666, 0.024981187656521797, -0.0073182773776352406, -0.038297150284051895, -0.016067195683717728, -0.006410370580852032, -0.011225027032196522, 0.012820741161704063, -0.009189114905893803, -0.01925862394273281, -0.02993340604007244, 0.012105421163141727, -0.0254213847219944, -0.006575444713234901, -0.02817261591553688, -0.025861581787467003, -0.012655667960643768, 0.034115277230739594, -0.03059370070695877, -0.00748335151001811, -0.006382858380675316, -0.005832612048834562, -0.015186801552772522, -0.01408630795776844, 0.029053010046482086, -0.026962075382471085, 0.012105421163141727, -0.056125134229660034, -0.004759631585329771, 0.0023798157926648855, 0.0016094708116725087, -0.01441645622253418, 0.0783550888299942, 0.026191730052232742, -0.013646110892295837, -0.04357951506972313, -0.019808871671557426, -0.0011486393632367253, -0.0038792372215539217, -0.017607884481549263, 0.012215470895171165, 0.03675645962357521, 0.044459909200668335, 0.017277738079428673, -0.029053010046482086, 0.0026962074916809797, 0.01045468170195818, -0.023110348731279373, 0.008363745175302029, -0.02090936340391636, 0.019698821008205414, -0.018378229811787605, -0.016727490350604057, 0.030813800171017647, 0.03301478549838066, -0.055464837700128555, 0.031474094837903976, 0.022229954600334167, -0.019478723406791687, -0.015186801552772522, 0.02333044819533825, 0.006850568111985922, 0.0024623526260256767, 0.03301478549838066, -0.012490593828260899, -0.017938032746315002, 0.0010454681469127536, -0.009134090505540371, -0.054144248366355896, 0.02333044819533825, 0.03477557376027107, -0.026631927117705345, -0.02674197591841221, -0.005062267184257507, -0.010179558768868446, -0.0005708806565962732, 0.01408630795776844, 0.011114977300167084, 0.01859832927584648, -0.0018708378775045276, 0.0016369831282645464, -0.01083985436707735, -0.019478723406791687, 0.022780202329158783, -0.004126848187297583, 0.032134391367435455, 0.02024906873703003, 0.007813499309122562, 0.00018656792235560715, 0.01859832927584648, -0.004512020852416754, 0.004126848187297583, -0.015626998618245125, -0.018268181011080742, -0.007098178844898939, -0.015626998618245125, -0.01815813221037388, 0.013921234756708145, 0.013811185024678707, 0.016617441549897194, 0.03543587028980255, 0.02024906873703003, 0.0010661024134606123, -0.015076751820743084, 0.003769187955185771, -0.011940347030758858, 0.0061627598479390144, -0.04401971399784088, -0.005640025716274977, -0.0009560531470924616, -0.023440496996045113, 0.03873734921216965, 0.005062267184257507, 0.01716768741607666, 0.001760788494721055, 0.002256010426208377, 0.013095865026116371, 0.011500149965286255, 0.019038526341319084, -0.006382858380675316, -0.0433594174683094, -0.0072632525116205215, -0.022119905799627304, 0.036536362022161484, 0.019698821008205414, 0.0018845939775928855, -0.029053010046482086, -0.004787143785506487, -0.02883291244506836, 0.005942661315202713, 0.045120205730199814, 0.0036316262558102608, 0.011665224097669125, 0.008253696374595165, 0.02509123645722866, 0.03323488309979439, 0.02718217298388481, -0.013040839694440365, 0.01782798394560814, 0.029053010046482086, -0.011280051432549953, 0.01216044556349516, -0.014196357689797878, 0.005640025716274977, 0.03059370070695877, -0.010124534368515015, -0.000997321680188179, -0.0004883437068201602, 0.004787143785506487, 0.009354189038276672, -0.007015641778707504, 0.009849410504102707, -0.02410079352557659, -0.0062177847139537334, -0.0031364045571535826, 0.004952217917889357, 0.020469166338443756, -0.029273109510540962, -0.01782798394560814, 0.004787143785506487, -0.024540990591049194, -0.012435569427907467, 0.017057638615369797, -0.0037967003881931305, 0.02267015166580677, -0.011335075832903385, 0.002448596525937319, 0.045560404658317566, 0.03125399723649025, 0.022229954600334167, 0.05898641422390938, 0.028392715379595757, 0.004044311121106148, -0.04181872680783272, 0.000254488957580179, 0.01254561822861433, -0.015737047418951988, -0.01496670302003622, 0.01925862394273281, 0.049302078783512115, -0.012325519695878029, -0.0017263981280848384, -0.0008425648557022214, 0.019038526341319084, -0.0073182773776352406, 0.018268181011080742, 0.030153503641486168, 0.055464837700128555, 0.04490010812878609, 0.019038526341319084, 0.04225892573595047, -0.022119905799627304, -0.015296850353479385, -0.0009285408305004239, -0.03741675615310669, -0.03961774334311485, 0.005254853516817093, 0.033454980701208115, 0.006272809114307165, 0.010894878767430782, -0.010069509036839008, 0.0026411828584969044, -0.010014484636485577, -0.020139018073678017, -0.01617724448442459, 0.015626998618245125, -0.010014484636485577, 0.03961774334311485, 0.0216797087341547, -0.004594557452946901, -0.00464958231896162, -0.006547932513058186, 0.029273109510540962, -0.009409213438630104, 0.015406900085508823, -0.011445125564932823, -0.013646110892295837, 0.008088622242212296, -0.023880694061517715, 0.013921234756708145, 0.005887636449187994, 0.05216335877776146, 0.011445125564932823, 0.013260938227176666, -0.046220697462558746, -0.019808871671557426, -0.008198671974241734, 0.016947589814662933, -0.020799314603209496, 0.02476108819246292, 0.0017883008113130927, -0.034115277230739594, -0.017607884481549263, -0.028612812981009483, 0.03983784094452858, -0.022780202329158783, -0.002256010426208377, 0.032794687896966934, 0.04093833267688751, 0.022229954600334167, 0.0002157997660106048, 0.013150889426469803, 0.0024761089589446783, -0.005832612048834562, 0.02993340604007244, 0.006933104712516069, -0.038957446813583374, -0.013756160624325275, -0.01584709621965885, -0.0025724018923938274, 0.011610199697315693, 0.00020634240354411304, 0.03191429376602173, 0.0019396186107769608, -0.016947589814662933, -0.049962375313043594, -0.04225892573595047, 0.0022284979932010174, -0.034555476158857346, -0.04974227771162987, -0.00352157698944211, 0.026852024719119072, -0.027732418850064278, -0.04115843027830124, -4.126848216401413e-05, 0.01683754101395607, 0.006272809114307165, 0.011059952899813652, -0.015516948886215687, 0.004181872587651014, -0.015626998618245125, 0.0021046926267445087, 0.03565596789121628, -0.038297150284051895, -0.01925862394273281, -0.054144248366355896, -0.02949320711195469, -0.003342746989801526, 0.026301778852939606, -0.013701136223971844, 0.005254853516817093, 0.021349560469388962, -0.013040839694440365, -0.023990744724869728, -0.018708378076553345, 0.012930790893733501, -0.006492907647043467, -0.025861581787467003, -0.02333044819533825, -0.02949320711195469, -0.014856653288006783, -0.017387786880135536, -0.020799314603209496, 0.013701136223971844, -0.008033597841858864, -0.034555476158857346, -0.0007841011392883956, -0.006740518845617771, -0.024981187656521797, -0.020799314603209496, -0.016067195683717728, 0.013426012359559536, -0.02333044819533825, -0.003906749654561281, -0.00608022278174758, 0.03873734921216965, -0.033454980701208115, -0.03873734921216965, 0.02817261591553688, 0.01716768741607666, -0.02509123645722866, -0.010399657301604748, 0.013811185024678707, 0.029053010046482086, -0.044459909200668335, 6.878080057504121e-06, -0.007868523709475994, 0.01254561822861433, 0.008143646642565727, 0.036536362022161484, 0.015957146883010864, 0.021789757534861565, -0.01083985436707735, -0.0424790233373642, -0.0014581530122086406, -0.008033597841858864, 0.0036591386888176203, 0.026852024719119072, 0.006630469113588333, 0.010674780234694481, -0.01650739274919033, 0.04401971399784088, -0.018708378076553345, 0.032134391367435455, -0.00453953305259347, 0.0005640026065520942, 0.008253696374595165, -0.030373603105545044, 0.03257458657026291, 0.007868523709475994, -0.0069055925123393536, 0.03059370070695877, 0.04842168465256691, 0.014636554755270481, 0.011390101164579391, 0.04291922226548195, 0.001169273629784584, 0.02200985699892044, -0.007593400776386261, 0.02509123645722866, -0.0508427694439888, 0.008363745175302029, 0.017387786880135536, 0.04490010812878609, -0.015626998618245125, 0.01045468170195818, 0.021789757534861565, 0.011720248498022556, -0.033454980701208115, 0.00453953305259347, -0.029053010046482086, 0.04468001052737236, -0.031033897772431374, 0.00018312888278160244, -0.005942661315202713, -0.010344632901251316, 0.04225892573595047, -0.009904435835778713, -0.05942661315202713, -0.009189114905893803, 0.025861581787467003, -0.01216044556349516, -0.004346946720033884, 0.013315963558852673, -0.008803942240774632, 0.0046220701187849045, -0.019368674606084824, 0.026191730052232742, 0.012050396762788296, 0.01815813221037388, -0.025641482323408127, -0.0012449325295165181, 0.0006327833980321884, -0.02751232124865055, 0.03389517962932587, 0.02443094179034233, 0.006300321314483881, -0.013370987959206104, 0.006575444713234901, 0.026631927117705345, 0.017387786880135536, -0.028062567114830017, -0.005887636449187994, 0.00021064121392555535, 0.019478723406791687, -0.00018656792235560715, 0.00891399197280407, 0.02443094179034233, 0.008638869039714336, -0.029273109510540962, -0.015406900085508823, 0.007373301777988672, -0.0011899078963324428, -0.0034665523562580347, -0.00304011139087379, 0.012765716761350632, 0.032134391367435455, 0.023110348731279373, -0.027952518314123154, 0.0007325155311264098, -0.05150306597352028, -0.018488280475139618, 0.016397343948483467, 0.0024073279928416014, -0.032134391367435455, -0.002269766526296735, 0.053704049438238144, -0.007098178844898939, -0.022560102865099907, -0.028062567114830017, -0.009794386103749275, -0.04159862920641899, -0.020359117537736893, 0.016287293285131454, -0.005915149115025997, -0.011995372362434864, -0.012325519695878029, -0.019148575142025948, -0.03675645962357521, 0.015406900085508823, 0.008803942240774632, -0.019478723406791687, -0.02509123645722866, 0.025641482323408127, -0.014306406490504742, -0.013811185024678707, -0.06558937579393387, -0.023110348731279373, -0.002022155560553074, 0.025531433522701263, -0.004759631585329771, -0.04291922226548195, 0.006107735447585583, 0.011335075832903385, 0.046220697462558746, -0.03059370070695877, 0.006768031045794487, 0.054144248366355896, -0.018378229811787605, 0.001843325444497168, 0.005447439383715391, -0.03961774334311485, 0.00858384370803833, 0.01441645622253418, -0.01408630795776844, 0.060307007282972336, 0.021569659933447838, 0.047981489449739456, 0.010124534368515015, 0.0174978356808424, -0.028392715379595757, -0.03125399723649025, 0.019148575142025948, 0.01892847754061222, 0.0072632525116205215, 0.02057921513915062, -0.008198671974241734, 0.0011555175296962261, -0.00946423877030611, 0.009024041704833508, -0.02883291244506836, 0.018818426877260208, -0.0029713306576013565, -0.014636554755270481, 0.011059952899813652, -0.02718217298388481, 0.013536062091588974, 0.003507820889353752, 0.029053010046482086, 0.0031776730902493, -0.016727490350604057, -0.012270495295524597, -0.04886188358068466, -0.0004212824278511107, 0.04732119292020798, -0.001258688629604876, 0.0003628187405411154, -0.024871138855814934, -0.005585001315921545, -0.0041543603874742985, 0.03785695508122444, -0.008528819307684898, 0.010399657301604748, 0.015076751820743084, -0.022780202329158783, -0.005997686181217432, 0.032794687896966934, 0.029713306576013565, 0.0174978356808424, -0.015626998618245125, -0.006327833980321884, 0.003906749654561281, 0.019368674606084824, -0.014306406490504742, -0.04115843027830124, 0.0216797087341547, -0.03323488309979439, -0.010344632901251316, -0.0045670452527701855, 0.02718217298388481, 0.005529976449906826, 0.004484508186578751, 0.021459611132740974, 0.007373301777988672, -0.002737476024776697, 0.014526505023241043, 0.0015750803286209702, -0.0508427694439888, -0.010399657301604748, 0.0016438611783087254, -0.014526505023241043, -0.02949320711195469, -0.016287293285131454, 0.03807705268263817, -0.005997686181217432, -0.0027237196918576956, 0.03059370070695877, 0.05062267184257507, 0.03565596789121628, -0.02200985699892044, -0.026631927117705345, -0.01859832927584648, -0.006657981779426336, -0.025641482323408127, 0.014306406490504742, -0.0007290765061043203, 0.002448596525937319, -0.009794386103749275, 0.02509123645722866, -0.00929916463792324, 0.0026686950586736202, 0.04710109159350395, -0.028392715379595757, -0.007373301777988672, 0.03301478549838066, -0.009629311971366405, -0.026521876454353333, -0.026631927117705345, -0.03609616681933403, 0.03367508202791214, 0.0174978356808424, -0.010069509036839008, -0.02883291244506836, 0.02057921513915062, -0.002847525291144848, 0.007648425176739693, 0.0057500749826431274, 0.045560404658317566, -0.008198671974241734, 0.029053010046482086, 0.010894878767430782, 0.00891399197280407, 0.008693893440067768, 0.013150889426469803, -0.017277738079428673, 0.0016369831282645464, -0.003961774054914713, -0.03873734921216965, -0.004677094519138336, -0.017938032746315002, 0.012105421163141727, -0.009904435835778713, -0.011830298230051994, 0.005695050582289696, -0.029273109510540962, 0.00720822811126709, 0.02476108819246292, -0.030813800171017647, -0.03301478549838066, -0.0033014784567058086, 0.012270495295524597, 0.042699120938777924, -0.028392715379595757, -0.008858967572450638, -0.03961774334311485, -0.008198671974241734, 0.017607884481549263, -0.008033597841858864, 0.03719665855169296, 0.0017057638615369797, -0.01061975583434105, -0.037636853754520416, 0.023880694061517715, 0.011885322630405426, 0.018488280475139618, 0.014526505023241043, 0.01782798394560814, -0.02333044819533825, 0.007153203245252371, 0.008198671974241734, -0.015406900085508823, 0.008693893440067768, 0.020359117537736893, -0.01441645622253418, -0.05458444356918335, 0.014636554755270481, -0.01408630795776844, 0.005915149115025997, 0.000832247722428292, -0.0011280052131041884, -0.0017745447112247348, -0.005860124249011278, 0.0005536854732781649, -0.0046220701187849045, 0.024651039391756058, 0.013756160624325275, -0.006025198381394148, -0.0433594174683094, 0.02674197591841221, -0.009189114905893803, -0.00464958231896162, -0.016287293285131454, -0.0028200128581374884, -0.04159862920641899, 0.0022422540932893753, -0.06426878273487091, 0.00720822811126709, 0.015076751820743084, -0.015296850353479385, 0.009904435835778713, -0.0349956713616848, 0.008308720774948597, -0.029713306576013565, -0.00907906610518694, -0.011830298230051994, -0.007373301777988672, 0.008528819307684898, 0.02575153298676014, 0.04203882813453674, 0.0087489178404212, -0.024871138855814934, 0.02300029993057251, -0.024540990591049194, -0.02234000526368618, 0.019698821008205414, -0.009354189038276672, -0.02641182765364647, -0.00352157698944211, -0.02641182765364647, -0.0011830298462882638, 0.04049813747406006, -0.008803942240774632, -0.011885322630405426, -0.012050396762788296, -0.025971630588173866, 0.010179558768868446, -0.015296850353479385, -0.006878080312162638, 0.015406900085508823, -0.01892847754061222, -0.030153503641486168, -0.01238054409623146, -0.0433594174683094, 0.021789757534861565, 0.0027237196918576956, -0.024871138855814934, -0.00720822811126709, -0.003604114055633545, 0.005199828650802374, -0.006740518845617771, -0.0006499785813502967, -0.03741675615310669, 0.001506299595348537, -0.007923548109829426, 0.015626998618245125, -0.005832612048834562, 0.008143646642565727, -0.05898641422390938, -0.006272809114307165, 0.0038792372215539217, -0.020689265802502632, 0.020028969272971153, -0.017057638615369797, 0.030813800171017647, -0.011830298230051994, 0.017277738079428673, 0.013095865026116371, 0.012930790893733501, -0.012105421163141727, 0.010344632901251316, -0.0005743196816183627, -0.007153203245252371, -0.023110348731279373, 0.008088622242212296, -0.0008528819307684898, -0.011555174365639687, 0.010729805566370487, -0.01650739274919033, 0.023550545796751976, -0.0049247052520513535, -0.006878080312162638, 0.00464958231896162, -0.08055607229471207, 0.012105421163141727, -0.024981187656521797, -0.05590503662824631, 0.0018570816610008478, 0.0021046926267445087, -0.021349560469388962, 0.013976259157061577, -0.05018247291445732, -0.012655667960643768, 0.018048083409667015, -0.014636554755270481, 0.014306406490504742, 0.008858967572450638, 0.025531433522701263, -0.0043744589202106, -0.004044311121106148, -3.202606239938177e-05, 0.016067195683717728, -0.014746603555977345, 0.03741675615310669, -0.023880694061517715, 0.010179558768868446, -0.02366059646010399, 0.04401971399784088, -0.027622370049357414, -0.0049247052520513535, -0.008528819307684898, 0.017607884481549263, -0.018488280475139618, -0.022450054064393044, -0.01584709621965885, -0.017607884481549263, 0.01859832927584648, 0.023880694061517715, 0.019368674606084824, -0.008803942240774632, -0.0019533748272806406, 0.03631626442074776, -0.009189114905893803, 0.0216797087341547, -0.0014719091122969985, 0.019698821008205414, -0.011114977300167084, -0.017057638615369797, 0.00453953305259347, 0.04908198118209839, 0.002998843090608716, -0.0013893721625208855, 0.009409213438630104, -0.047541290521621704, -0.03433537483215332, -0.002159717259928584, -0.011280051432549953, 0.010894878767430782, 0.02949320711195469, 0.0072632525116205215, -5.502464046003297e-05, -0.015626998618245125, 0.01782798394560814, 0.012490593828260899, 0.005474952049553394, 0.028612812981009483, 0.012050396762788296, 0.020028969272971153, 0.021789757534861565, 0.011885322630405426, 0.005997686181217432, 0.020359117537736893, 0.01100492849946022, -0.008198671974241734, 0.007868523709475994, -0.030153503641486168, 0.013811185024678707, 0.009024041704833508, -0.006740518845617771, 0.003163916990160942, 0.024651039391756058, -0.032134391367435455, -0.0016851297114044428, 0.004869680851697922, -0.010894878767430782, 0.004512020852416754, 0.008033597841858864, 0.003961774054914713, 0.027952518314123154, 0.018378229811787605, -0.011775272898375988, 0.003026355290785432, -0.015737047418951988, 0.00946423877030611, 0.019478723406791687, 0.0032877223566174507, 0.009849410504102707, -0.004787143785506487, -0.02509123645722866, -0.019698821008205414, 0.0006602957146242261, -0.0316941924393177, 0.017938032746315002, 0.006713006179779768, 0.016617441549897194, 0.017607884481549263, -0.004512020852416754, -0.01117000263184309, 0.004814655985683203, 0.0127106923609972, 0.008088622242212296, 0.008969016373157501, 0.023440496996045113, 0.05590503662824631, -0.010124534368515015, 0.002352303359657526, 0.04225892573595047, -0.018378229811787605, -0.035215768963098526, -0.05018247291445732, 0.019698821008205414, 0.023880694061517715, 0.014856653288006783, -0.022780202329158783, 0.011610199697315693, -0.005777587182819843, -0.03961774334311485, 0.006465395446866751, -0.018488280475139618, 0.0216797087341547, 0.0316941924393177, 0.01617724448442459, -0.011390101164579391, -0.02057921513915062, -0.02993340604007244, 0.007648425176739693, -0.022119905799627304, 0.01028960756957531, 0.00858384370803833, -0.00042300194036215544, 0.002090936293825507, 0.03059370070695877, 0.013315963558852673, -0.006630469113588333, -0.01859832927584648, 0.009189114905893803, 0.01441645622253418, -0.026521876454353333, 0.029273109510540962, 0.010949904099106789, -0.007015641778707504, 0.015626998618245125, -0.00619027204811573, 0.03565596789121628, 0.007923548109829426, -0.0034527962561696768, -0.005777587182819843, 0.019808871671557426, -0.0023798157926648855, 0.010729805566370487, 0.004016798920929432, -0.01716768741607666, -0.029713306576013565, 0.026631927117705345, 0.000997321680188179, -0.03543587028980255, 0.034555476158857346, -0.002173473360016942, -0.029053010046482086, -0.006052710581570864, 0.0032326977234333754, 0.02817261591553688, -0.01083985436707735, 0.004319434519857168, -0.02443094179034233, 0.023110348731279373, 0.016727490350604057, -0.009739361703395844, 0.019698821008205414, 0.028612812981009483, 0.040057938545942307, 0.0316941924393177, 0.013260938227176666, -0.009024041704833508, -0.01238054409623146, 0.009684337303042412, 0.05106286704540253, -0.015406900085508823, -0.013370987959206104, -0.01958877220749855, -0.011885322630405426, -0.00522734085097909, 0.016397343948483467, -0.027622370049357414, 0.023880694061517715, 0.006740518845617771, -0.026631927117705345, -0.022560102865099907, 0.007373301777988672, 0.011114977300167084, 0.03983784094452858, -0.017607884481549263, -0.0014375187456607819, 0.026962075382471085, 0.014526505023241043, 0.0008803942473605275, -0.008143646642565727, 0.006630469113588333, 0.04093833267688751, -0.032134391367435455, -0.020469166338443756, 0.015957146883010864, -0.03235448896884918, -0.03543587028980255, -0.00720822811126709, 0.029273109510540962, -0.04027803614735603, 0.0062177847139537334, -0.02300029993057251, 0.03807705268263817, 0.0002630865783430636, -0.00720822811126709, -0.01716768741607666, -0.004512020852416754, -0.007593400776386261, -0.012655667960643768, -0.014196357689797878, 0.009794386103749275, -0.0058050998486578465, 0.014196357689797878, -0.04820158705115318, 0.0034665523562580347, 0.03939764201641083, -0.024651039391756058, -0.016947589814662933, 0.0004539532819762826, -0.00929916463792324, 0.01408630795776844, 0.022780202329158783, -0.024540990591049194, 0.03719665855169296, -0.02443094179034233, -0.010729805566370487, 0.0007737840060144663, -0.02575153298676014, 0.010014484636485577, -0.0069055925123393536, -0.006575444713234901, -0.015406900085508823, -0.0012036639964208007, 0.03125399723649025, -0.001994643360376358, -0.008693893440067768, -0.019368674606084824, -0.003026355290785432, 0.017387786880135536, -0.005832612048834562, 0.009354189038276672, -0.007428326644003391, -0.0029025499243289232, 0.004456995986402035, 0.046220697462558746, 0.006960617378354073, 0.047981489449739456, -0.021569659933447838, -0.006878080312162638, -0.011555174365639687, -0.011225027032196522, -0.014636554755270481, -0.032794687896966934, -0.009904435835778713, 0.015076751820743084, -0.01815813221037388, 0.023770645260810852, 0.018708378076553345, -0.047541290521621704, 0.01238054409623146, 0.015516948886215687, 0.017717935144901276, 0.014306406490504742, -0.04908198118209839, -0.030373603105545044, 0.019698821008205414, -0.012105421163141727, -0.024651039391756058, 0.03191429376602173, -0.017607884481549263, 0.008033597841858864, 0.0031776730902493, 0.022560102865099907, 0.006025198381394148, 0.0015750803286209702, 0.0049247052520513535, -0.01408630795776844, 0.008418770506978035, 0.0018020570278167725, 0.001843325444497168, -0.01892847754061222, 0.044459909200668335, 0.00748335151001811, -0.0073182773776352406, 0.01496670302003622, -0.007923548109829426, -0.03389517962932587, 0.00619027204811573, -0.003934261854737997, -0.04468001052737236, -0.004291921854019165, -0.013811185024678707, 0.0174978356808424, -0.030153503641486168, -0.0031501606572419405, -0.02993340604007244, -0.0045670452527701855, -0.07131193578243256, -0.019698821008205414, -0.005667537916451693, 0.016947589814662933, 0.041378531605005264, 0.017607884481549263, 0.018378229811787605, -0.020139018073678017, -0.010894878767430782, 0.0019808870274573565, 0.006795543245971203, -0.05282365530729294, -0.013260938227176666, 0.02641182765364647, -0.01496670302003622, 0.016287293285131454, -0.015737047418951988, 0.012765716761350632, 0.0174978356808424, 0.025971630588173866, 0.010949904099106789, -0.027402272447943687, 0.007758474443107843, -0.025641482323408127, -0.022229954600334167, 0.03873734921216965, 0.02101941406726837, 0.032794687896966934, -0.024651039391756058, -0.03059370070695877, 0.0003903310571331531, 0.010784829966723919, -0.02949320711195469, -0.030373603105545044, 0.021129462867975235, -0.015957146883010864, 0.005557488650083542, 0.007593400776386261, -0.0003077940782532096, 0.03125399723649025, 0.006878080312162638, -0.013921234756708145, -0.007098178844898939, -0.00037141633220016956, 0.01061975583434105, 0.0006465395563282073, 0.02057921513915062, 0.00304011139087379, 0.008143646642565727, -0.02101941406726837, 0.0042093852534890175, 0.006575444713234901, -0.005034754518419504, 0.02300029993057251, -0.016947589814662933, -0.027952518314123154, 0.03191429376602173, 0.02575153298676014, -0.007813499309122562, -0.025531433522701263, 0.0013068352127447724, 0.026301778852939606, 0.005667537916451693, 0.014526505023241043, -0.013701136223971844, -0.011225027032196522, 0.0016576172783970833, -0.021349560469388962, -0.0033977716229856014, -0.01958877220749855, 0.024981187656521797, -0.007373301777988672, 0.03609616681933403, 0.045120205730199814, 0.00748335151001811, -0.06074720621109009, 0.0014031283790245652, 0.023440496996045113, -0.012270495295524597, -0.016397343948483467, -0.022560102865099907, 0.023440496996045113, 0.016067195683717728, -0.006740518845617771, 0.010014484636485577, -0.004401971120387316, -0.01287576649338007, -0.006933104712516069, -0.014746603555977345, -0.0174978356808424, -0.03323488309979439, -0.002035911660641432, 0.014526505023241043, 0.031033897772431374, -0.015626998618245125, 0.0058050998486578465, 0.009794386103749275, -0.007978573441505432, -0.0016920077614486217, 0.014636554755270481, -0.053043752908706665, -0.0012174202129244804, -0.01925862394273281, 0.01287576649338007, 0.040718235075473785, 0.011940347030758858, -0.013260938227176666, -0.01045468170195818, 0.029053010046482086, 0.023770645260810852, 0.015626998618245125, 0.013811185024678707, 0.0212395116686821, 0.002200985560193658, 0.018268181011080742, -0.01859832927584648, -0.028612812981009483, -0.02993340604007244, -0.008308720774948597, 0.011555174365639687, 0.015406900085508823, -0.03301478549838066, 0.002200985560193658, 0.008528819307684898, 0.03191429376602173, 0.02751232124865055, 0.004126848187297583, -0.001747032394632697, -0.008693893440067768, 0.01782798394560814, 0.021569659933447838, 0.005942661315202713, -0.010234583169221878, 0.006272809114307165, -0.010069509036839008, -0.016947589814662933, -0.006327833980321884, -0.0062177847139537334, -0.0072632525116205215, 0.0030813799239695072, -0.014526505023241043, -0.005585001315921545, 0.053704049438238144, 0.008528819307684898, -0.00011004928092006594, -0.008198671974241734, -0.0127106923609972, 0.005557488650083542, 0.001169273629784584, 0.02267015166580677, -0.013866209425032139, -0.012490593828260899, 0.025311335921287537, 0.009574287571012974, -0.01061975583434105, 0.002434840425848961, 0.020359117537736893, 0.01441645622253418, 0.015737047418951988, 0.043139319866895676, 0.014031283557415009, 0.04776138812303543, -0.0003198307240381837, -0.013426012359559536, -0.010344632901251316, 0.01100492849946022, -0.0063553461804986, 0.011775272898375988, 0.0035490894224494696, 0.025971630588173866, -0.009574287571012974, -0.024871138855814934, -0.022780202329158783, 0.01254561822861433, 0.0391775444149971, 0.01650739274919033, -0.005667537916451693, -0.010069509036839008, -0.004456995986402035, -0.008253696374595165, -0.016067195683717728, -0.013591086491942406, 0.045120205730199814, 0.0024898650590330362, -0.007153203245252371, 0.026852024719119072, -0.040718235075473785, -0.00946423877030611, -0.006740518845617771, -0.023880694061517715, -0.003507820889353752, 0.006768031045794487, -0.026301778852939606, -0.030153503641486168, -0.013260938227176666, 0.001513177645392716, 0.031033897772431374, 0.03741675615310669, -0.02993340604007244, -0.006685493979603052, 0.016287293285131454, 0.005199828650802374, -0.026631927117705345, -0.018048083409667015, -0.02267015166580677, 0.017607884481549263, 0.0005227340734563768, -0.02575153298676014, -0.0026549389585852623, -0.022119905799627304, 0.013701136223971844, -0.03235448896884918, 0.040718235075473785, -0.02674197591841221, 0.026631927117705345, -0.005970173515379429, 0.03301478549838066, 0.007373301777988672, 0.013205913826823235, 0.0028200128581374884, 0.05810602009296417, -0.018378229811787605, 0.02784246951341629, -0.01496670302003622, 0.03301478549838066, -0.019478723406791687, 0.002159717259928584, -0.007098178844898939, -0.031033897772431374, -0.023110348731279373, -0.011885322630405426, -0.005915149115025997, 0.013536062091588974, -0.0058050998486578465, 0.017717935144901276, 0.0021184487268328667, -0.029273109510540962, 0.013811185024678707, 0.008308720774948597, -0.0006327833980321884, 0.01441645622253418, 0.0073182773776352406, 0.0316941924393177, -0.030373603105545044, -0.024981187656521797, 0.04093833267688751, 0.013921234756708145, 0.013150889426469803, -0.01892847754061222, 0.0053373901173472404, -0.011775272898375988, 0.01216044556349516, 0.010509707033634186, 0.021459611132740974, 0.053043752908706665, -0.02608167938888073, 0.014636554755270481, 0.02883291244506836, 0.0014787872787564993, 0.03191429376602173, 0.02784246951341629, -0.02949320711195469, 0.014526505023241043, -0.01028960756957531, 0.005722562782466412, -0.04203882813453674, -0.017717935144901276, -0.029273109510540962, -0.03323488309979439, -0.013646110892295837, 0.02641182765364647, -0.01617724448442459, 0.015406900085508823, -0.005970173515379429, 0.007813499309122562, -0.003507820889353752, -0.005529976449906826, 0.016397343948483467, -0.0032877223566174507, -0.02949320711195469, 0.020359117537736893, 0.017277738079428673, -0.01496670302003622, 0.005474952049553394, 0.019038526341319084, 0.014526505023241043, -0.03609616681933403, 0.021349560469388962, 0.001760788494721055, 0.046880993992090225, -0.006768031045794487, -0.01496670302003622, -0.01496670302003622, -0.0174978356808424, -0.008143646642565727, 0.038957446813583374, 0.007813499309122562, 0.0022972787264734507, -0.011500149965286255, -0.0004040872154291719, 0.0003662577655632049, 0.02509123645722866, 0.0708717405796051, -0.007428326644003391, 0.029053010046482086, 0.015737047418951988, -0.010729805566370487, -0.01584709621965885, 0.01782798394560814, -0.013811185024678707, 0.006492907647043467, -0.04534030333161354, -0.025641482323408127, -0.00704315397888422, -0.008803942240774632, -0.00024761087843216956, -0.0007806621142663062, 0.030373603105545044, -0.012765716761350632, 0.013976259157061577, -0.022450054064393044, -0.007923548109829426, 0.03367508202791214, 0.018488280475139618, 0.004484508186578751, 0.044459909200668335, 0.00037141633220016956, -0.0072632525116205215, 0.006465395446866751, 0.01083985436707735, -0.023110348731279373, -0.005062267184257507, -0.010344632901251316, -0.02751232124865055, 0.021129462867975235, -0.000254488957580179, 0.022450054064393044, 0.02575153298676014, -0.00858384370803833, -0.043139319866895676, 0.03257458657026291, 0.028392715379595757, 0.012655667960643768, 0.02410079352557659, 0.020139018073678017, -0.022780202329158783, -0.016287293285131454, -0.03125399723649025, 0.017938032746315002, -0.003851725021377206, -0.011940347030758858, -0.034115277230739594, -0.006685493979603052, -0.015406900085508823, -0.0057500749826431274, 0.00720822811126709, -0.018378229811787605, 0.001176151679828763, 0.029053010046482086, 0.020139018073678017, 0.01650739274919033, 0.013646110892295837, 0.023550545796751976, 0.0008425648557022214, 0.03477557376027107, -0.05106286704540253, -0.007373301777988672, -0.016727490350604057, 0.02200985699892044, 0.003604114055633545, -0.00619027204811573, -0.002613670425489545, 0.005640025716274977, 0.0072632525116205215, -0.01028960756957531, -0.011500149965286255, 0.034555476158857346, -0.05326385423541069, -0.008253696374595165, -0.030153503641486168, 0.032794687896966934, 0.020359117537736893, 0.01815813221037388, 0.00022009856184013188, -0.0006155881565064192, -0.03543587028980255, 0.033454980701208115, 0.03719665855169296, -0.01925862394273281, -0.016287293285131454, 0.026962075382471085, -0.030153503641486168, 0.0010248339967802167, -0.019478723406791687, 0.006410370580852032, 0.012600642628967762, 0.006025198381394148, 0.017607884481549263, -0.024651039391756058, -0.015076751820743084, 0.007648425176739693, -0.029273109510540962, -0.013536062091588974, 0.0010661024134606123, -0.024981187656521797, 0.029713306576013565, -0.006300321314483881, -0.013260938227176666, -0.007703450042754412, 0.01083985436707735, 0.015957146883010864, 0.02366059646010399, -0.024651039391756058, 0.020689265802502632, -0.02432089112699032, -0.003989286720752716, -0.0508427694439888, 0.007648425176739693, -0.026962075382471085, 0.005309877917170525, 0.0316941924393177, 0.020028969272971153, 0.0316941924393177, 0.015957146883010864, -0.0032877223566174507, -0.0016851297114044428, 0.01958877220749855, -0.014196357689797878, 0.034555476158857346, -0.011830298230051994, 0.013866209425032139, -0.010564731433987617, 0.0027237196918576956, -0.004897193051874638, -0.016287293285131454, 0.04115843027830124, 0.006685493979603052, 0.0037141633220016956, -0.009739361703395844, -0.01100492849946022, 0.009684337303042412, -0.004704606719315052, 0.027292221784591675, 0.006988129578530788, -0.013426012359559536, -0.006245296914130449, 0.011720248498022556, 0.04357951506972313, 0.005612513516098261, -0.008088622242212296, 0.004071823321282864, 0.011555174365639687, -0.0030676238238811493, 0.021569659933447838, 0.04842168465256691, 0.008363745175302029, -0.024651039391756058, 0.02443094179034233, -0.04776138812303543, 0.06074720621109009, 0.045120205730199814, -0.021569659933447838, 0.0127106923609972, 0.011225027032196522, -0.008638869039714336, 0.01925862394273281, 0.022890251129865646, -0.01991892047226429, -0.02267015166580677, 0.03609616681933403],
   12
                 "numCandidates": 500,
   13
                 "limit": 50
   14
                 }
   15
               }
   16
             ],
   17
             "fullTextPipeline": [
   18
               {
   19
                 "$search": {
   20
                   "index": "hybrid-full-text-search",
   21
                   "text": {
   22
                     "query": "charming animal",
   23
                     "path": "fullplot",
   24
                     "fuzzy": {}
   25
                   }
   26
                 }
   27
               },
   28
               { "$limit": 50 }
   29
             ]
   30
           }
   31
         },
   32
         "combination": {
   33
           "weights": {
   34
             "vectorPipeline": 0.5,
   35
             "fullTextPipeline": 0.5
   36
           }
   37
         },
   38
         "scoreDetails": true
   39
       }
   40
     },
   41
     {
   42
       "$project": {
   43
         "_id": 1,
   44
         "title": 1,
   45
         "fullplot": 1,
   46
         "scoreDetails": {"$meta": "scoreDetails"}
   47
       }
   48
     },
   49
     {
   50
       "$limit": 10
   51
     }
   52
   ]

   Hide output

   1
   {
   2
     "_id": {
   3
       "$oid": "573a1397f29313caabce80f6"
   4
     },
   5
     "title": "Gauche the Cellist",
   6
     "fullplot": "A cellist in a small orchestra receives help from animals to help him practice his music.",
   7
     "scoreDetails": {
   8
       "value": 0.015527202696196438,
   9
       "description": "value output by reciprocal rank fusion algorithm, computed as sum of (weight * (1 / (60 + rank))) across input pipelines from which this document is output, from:",
   10
       "details": [
   11
         {
   12
           "inputPipelineName": "fullTextPipeline",
   13
           "rank": 7,
   14
           "weight": 0.5,
   15
           "value": 2.6925015449523926,
   16
           "details": []
   17
         },
   18
         {
   19
           "inputPipelineName": "vectorPipeline",
   20
           "rank": 2,
   21
           "weight": 0.5,
   22
           "value": 0.6968950033187866,
   23
           "details": []
   24
         }
   25
       ]
   26
     }
   27
   }
   28
   {
   29
     "_id": {
   30
       "$oid": "573a13b4f29313caabd4070d"
   31
     },
   32
     "title": "Paragraph 78",
   33
     "fullplot": "This is a wonderful movie about a group of men frontier the Nashville area who like to make puppets out of real animals",
   34
     "scoreDetails": {
   35
       "value": 0.013793759512937594,
   36
       "description": "value output by reciprocal rank fusion algorithm, computed as sum of (weight * (1 / (60 + rank))) across input pipelines from which this document is output, from:",
   37
       "details": [
   38
         {
   39
           "inputPipelineName": "fullTextPipeline",
   40
           "rank": 12,
   41
           "weight": 0.5,
   42
           "value": 2.5729734897613525,
   43
           "details": []
   44
         },
   45
         {
   46
           "inputPipelineName": "vectorPipeline",
   47
           "rank": 13,
   48
           "weight": 0.5,
   49
           "value": 0.681915819644928,
   50
           "details": []
   51
         }
   52
       ]
   53
     }
   54
   }
   55
   {
   56
     "_id": {
   57
       "$oid": "573a1394f29313caabce074d"
   58
     },
   59
     "title": "Perri",
   60
     "fullplot": "This True Life Fantasy follows and shows how the life of a female squirrel, Perri, in the forest is filled with danger and fraught with peril. When not fleeing her natural enemy, the Marten, Perri finds time to fall in love with her prince-charming male squirrel.",
   61
     "scoreDetails": {
   62
       "value": 0.013144841269841268,
   63
       "description": "value output by reciprocal rank fusion algorithm, computed as sum of (weight * (1 / (60 + rank))) across input pipelines from which this document is output, from:",
   64
       "details": [
   65
         {
   66
           "inputPipelineName": "fullTextPipeline",
   67
           "rank": 3,
   68
           "weight": 0.5,
   69
           "value": 3.0468099117279053,
   70
           "details": []
   71
         },
   72
         {
   73
           "inputPipelineName": "vectorPipeline",
   74
           "rank": 36,
   75
           "weight": 0.5,
   76
           "value": 0.6600974798202515,
   77
           "details": []
   78
         }
   79
       ]
   80
     }
   81
   }
   82
   {
   83
     "_id": {
   84
       "$oid": "573a139af29313caabcf089f"
   85
     },
   86
     "fullplot": "Dr. John Dolittle has the world in his hands: A beautiful wife at his side, two adorable daughters and a career that could not go better. One night, he nearly runs over a dog with his car. The dog yells \"bonehead\" and disappears. From then on, his childhood ability is back: To communicate with animals. Unfortunately, the word of Dolittle's ability is spreading quickly. Soon, many animals from rat to horse flock to his place to get medical advice. But his colleagues suspect he's going mad, and as the clinic Dolittle used to work for is about to being taken over for a huge amount of money, many decisions have to be made. Believe him? Put him into a mental institution? Sell the clinic? But also his family is close to breaking apart. Until a circus tiger falls seriously ill.",
   87
     "title": "Doctor Dolittle",
   88
     "scoreDetails": {
   89
       "value": 0.013010540184453228,
   90
       "description": "value output by reciprocal rank fusion algorithm, computed as sum of (weight * (1 / (60 + rank))) across input pipelines from which this document is output, from:",
   91
       "details": [
   92
         {
   93
           "inputPipelineName": "fullTextPipeline",
   94
           "rank": 32,
   95
           "weight": 0.5,
   96
           "value": 2.167940855026245,
   97
           "details": []
   98
         },
   99
         {
   100
           "inputPipelineName": "vectorPipeline",
   101
           "rank": 6,
   102
           "weight": 0.5,
   103
           "value": 0.6903904676437378,
   104
           "details": []
   105
         }
   106
       ]
   107
     }
   108
   }
   109
   {
   110
     "_id": {
   111
       "$oid": "573a1395f29313caabce1b5f"
   112
     },
   113
     "title": "Hatari!",
   114
     "fullplot": "John Wayne and his ensemble cast cavort over the African landscape filling orders from zoos for wild animals. Bruce Cabot plays \"the Indian\", a womanizing sharpshooter who is gored by a rhino in the opening scenes of the film. This becomes a running theme through the movie; their bad luck in catching rhinos, and provides the climactic ending chase. While Bruce is in the hospital, Elsa Martinelli shows up as a woman photographer from a Swiss zoo, and John wants to send her packing. She strongarms the Duke into letting her stay by promising that her zoo will buy most of their animals this season if she's allowed to go along on the hunts and take photos. Hardy Kruger, Gerard Blain, Michelle Girardon and Valentin de Vargas round out the group. They traipse over the African landscape capturing animals; Elsa also has a running gag where she collects baby elephants as the movie goes along. In the end she's acquired three of them.",
   115
     "scoreDetails": {
   116
       "value": 0.01259106746911625,
   117
       "description": "value output by reciprocal rank fusion algorithm, computed as sum of (weight * (1 / (60 + rank))) across input pipelines from which this document is output, from:",
   118
       "details": [
   119
         {
   120
           "inputPipelineName": "fullTextPipeline",
   121
           "rank": 17,
   122
           "weight": 0.5,
   123
           "value": 2.464411973953247,
   124
           "details": []
   125
         },
   126
         {
   127
           "inputPipelineName": "vectorPipeline",
   128
           "rank": 22,
   129
           "weight": 0.5,
   130
           "value": 0.6660783886909485,
   131
           "details": []
   132
         }
   133
       ]
   134
     }
   135
   }
   136
   {
   137
     "_id": {
   138
       "$oid": "573a1393f29313caabcde3af"
   139
     },
   140
     "title": "Mighty Joe Young",
   141
     "fullplot": "In Africa, the girl Jill Young trades a baby gorilla with two natives and raises the animal. Twelve years later, the talkative and persuasive promoter Max O'Hara organizes a safari to Africa with the Oklahoma cowboy Gregg to bring attractions to his new night-club in Hollywood. They capture several lions and out of blue, they see a huge gorilla nearby their camping and they try to capture the animal. However, the teenager Jill Young stops the men that intended to kill her gorilla. Max seduces Jill with a fancy life in Hollywood and she signs a contract with him where the gorilla Joseph \"Joe\" Young would be the lead attraction. Soon she realizes that her dream is a nightmare to Joe and she asks Max to return to Africa. However he persuades her to stay a little longer in the show business. But when three alcoholic costumers give booze to Joe, the gorilla destroys the spot and is sentenced by the justice to be sacrificed. Will Jill, Gregg and Max succeed in saving Joe?",
   142
     "scoreDetails": {
   143
       "value": 0.012579113924050634,
   144
       "description": "value output by reciprocal rank fusion algorithm, computed as sum of (weight * (1 / (60 + rank))) across input pipelines from which this document is output, from:",
   145
       "details": [
   146
         {
   147
           "inputPipelineName": "fullTextPipeline",
   148
           "rank": 20,
   149
           "weight": 0.5,
   150
           "value": 2.3966262340545654,
   151
           "details": []
   152
         },
   153
         {
   154
           "inputPipelineName": "vectorPipeline",
   155
           "rank": 19,
   156
           "weight": 0.5,
   157
           "value": 0.6716707944869995,
   158
           "details": []
   159
         }
   160
       ]
   161
     }
   162
   }
   163
   {
   164
     "_id": {
   165
       "$oid": "573a13bcf29313caabd55f51"
   166
     },
   167
     "title": "The Missing Lynx",
   168
     "fullplot": "A group of animals look for a way off of an eccentric billionaire's own personal Noah's Ark.",
   169
     "scoreDetails": {
   170
       "value": 0.012303436225975538,
   171
       "description": "value output by reciprocal rank fusion algorithm, computed as sum of (weight * (1 / (60 + rank))) across input pipelines from which this document is output, from:",
   172
       "details": [
   173
         {
   174
           "inputPipelineName": "fullTextPipeline",
   175
           "rank": 8,
   176
           "weight": 0.5,
   177
           "value": 2.674750566482544,
   178
           "details": []
   179
         },
   180
         {
   181
           "inputPipelineName": "vectorPipeline",
   182
           "rank": 41,
   183
           "weight": 0.5,
   184
           "value": 0.6568813920021057,
   185
           "details": []
   186
         }
   187
       ]
   188
     }
   189
   }
   190
   {
   191
     "_id": {
   192
       "$oid": "573a1398f29313caabcea708"
   193
     },
   194
     "fullplot": "Returning from a hunting trip in the forest, the Henderson family's car hits an animal in the road. At first they fear it was a man, but when they examine the \"body\" they find it's a \"bigfoot\". They think it's dead so they decide to take it home (there could be some money in this..). As you guessed, \"it\" isn't dead. Far from being the ferocious monster they fear \"Harry\" to be, he's a friendly giant. In their attempts to keep Harry a secret, the Henderson's have to hide him from the authorities and a man, who has made it his goal in life, to catch a \"bigfoot\".",
   195
     "title": "Harry and the Hendersons",
   196
     "scoreDetails": {
   197
       "value": 0.009662061239731142,
   198
       "description": "value output by reciprocal rank fusion algorithm, computed as sum of (weight * (1 / (60 + rank))) across input pipelines from which this document is output, from:",
   199
       "details": [
   200
         {
   201
           "inputPipelineName": "fullTextPipeline",
   202
           "rank": 44,
   203
           "weight": 0.5,
   204
           "value": 2.039764165878296,
   205
           "details": []
   206
         },
   207
         {
   208
           "inputPipelineName": "vectorPipeline",
   209
           "rank": 43,
   210
           "weight": 0.5,
   211
           "value": 0.654127836227417,
   212
           "details": []
   213
         }
   214
       ]
   215
     }
   216
   }
   217
   {
   218
     "_id": {
   219
       "$oid": "573a13a3f29313caabd0d0a8"
   220
     },
   221
     "fullplot": "Dr. John Dolittle the beloved doctor is back, but this time around he plays cupid to bumbling circus bear Archie as he's so smitten by a Pacific Western bear female, Ava. Dr. Dolittle must help a group of forest creatures to save their forest. But with the aid of his mangy, madcap animal friends, Dr. Dolittle must teach Archie the ways of true romance in time to save his species and his home before their habit is gone. So John held a meeting for every animal in the forest to not give up without a fight no matter what kind of animal expression they have and everyone agrees to do it and save their home.",
   222
     "title": "Dr. Dolittle 2",
   223
     "scoreDetails": {
   224
       "value": 0.00819672131147541,
   225
       "description": "value output by reciprocal rank fusion algorithm, computed as sum of (weight * (1 / (60 + rank))) across input pipelines from which this document is output, from:",
   226
       "details": [
   227
         {
   228
           "inputPipelineName": "fullTextPipeline",
   229
           "rank": 1,
   230
           "weight": 0.5,
   231
           "value": 3.2179136276245117,
   232
           "details": []
   233
         },
   234
         {
   235
           "inputPipelineName": "vectorPipeline",
   236
           "rank": "NA"
   237
         }
   238
       ]
   239
     }
   240
   }
   241
   {
   242
     "_id": {
   243
       "$oid": "573a13a6f29313caabd174a6"
   244
     },
   245
     "title": "Bear's Kiss",
   246
     "fullplot": "A fairy tale-like love story between young circus artist Lola and the bear Misha, who one day transforms into a human.",
   247
     "scoreDetails": {
   248
       "value": 0.00819672131147541,
   249
       "description": "value output by reciprocal rank fusion algorithm, computed as sum of (weight * (1 / (60 + rank))) across input pipelines from which this document is output, from:",
   250
       "details": [
   251
         {
   252
           "inputPipelineName": "fullTextPipeline",
   253
           "rank": "NA"
   254
         },
   255
         {
   256
           "inputPipelineName": "vectorPipeline",
   257
           "rank": 1,
   258
           "weight": 0.5,
   259
           "value": 0.7064177393913269,
   260
           "details": []
   261
         }
   262
       ]
   263
     }
   264
   }