> ## Documentation Index
> Fetch the complete documentation index at: https://unstructured-53-docs-243-plugins.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Milvus
This page was recently updated. What do you think about it? [Let us know!](https://smart-forms.saasjet.com/external?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJjbGllbnRLZXkiOiIzZGQ5OTEzYy04Mzg1LTNkNDAtYWQ1MS03NmM0Nzg5YjAxOGUiLCJpYXQiOjE3MTQ0MzI1ODU5MjF9.m5gHGCOHt_UgOs-JCdTdEHRcQUNftvLGWeKzK2o2pQ4).
Batch process all your records to store structured outputs in Milvus.
The requirements are as follows.
* For the [Unstructured UI](/ui/overview) or the [Unstructured API](/api-reference/overview), only Milvus cloud-based instances (such as Zilliz Cloud, and Milvus on IBM watsonx.data) are supported.
* For [Unstructured Ingest](/ingestion/overview), Milvus local and cloud-based instances are supported.
The following video shows how to fulfill the minimum set of requirements for Milvus cloud-based instances, demonstrating Milvus on IBM watsonx.data:
* For Zilliz Cloud, you will need:
* A [Zilliz Cloud account](https://cloud.zilliz.com/signup).
* A [Zilliz Cloud cluster](https://docs.zilliz.com/docs/create-cluster).
* The URI of the cluster, also known as the cluster's *public endpoint*, which takes a format such as
`https://..-.cloud.zilliz.com`.
[Get the cluster's public endpoint](https://docs.zilliz.com/docs/manage-cluster#connect-to-cluster).
* The token to access the cluster. [Get the cluster's token](https://docs.zilliz.com/docs/manage-cluster#connect-to-cluster).
* The name of the [database](https://docs.zilliz.com/docs/database#create-database) in the instance.
* The name of the [collection](https://docs.zilliz.com/docs/manage-collections-console#create-collection) in the database.
The collection must have a a defined schema before Unstructured can write to the collection. The minimum viable
schema for Unstructured contains only the fields `element_id`, `embeddings`, and `record_id`, as follows:
| Field Name | Field Type | Max Length | Dimension | Index | Metric Type |
| -------------------------------- | ----------------- | ---------- | --------- | ------------- | ----------- |
| `element_id` (primary key field) | **VARCHAR** | `200` | -- | -- | -- |
| `embeddings` (vector field) | **FLOAT\_VECTOR** | -- | `3072` | Yes (Checked) | **Cosine** |
| `record_id` | **VARCHAR** | `200` | -- | -- | -- |
* For Milvus on IBM watsonx.data, you will need:
* An [IBM Cloud account](https://cloud.ibm.com/registration).
* The [IBM watsonx.data subscription plan](https://cloud.ibm.com/docs/watsonxdata?topic=watsonxdata-getting-started).
* A [Milvus service instance in IBM watsonx.data](https://cloud.ibm.com/docs/watsonxdata?topic=watsonxdata-adding-milvus-service).
* The URI of the instance, which takes the format of `https://`, followed by instance's **GRPC host**, followed by a colon and the **GRPC port**.
This takes the format of `https://:`.
[Get the instance's GRPC host and GRPC port](https://cloud.ibm.com/docs/watsonxdata?topic=watsonxdata-conn-to-milvus).
* The name of the [database](https://milvus.io/docs/manage_databases.md) in the instance.
* The name of the [collection](https://milvus.io/docs/manage-collections.md) in the database. Note the collection requirements at the end of this section.
* The uername and password to access the instance.
The username for Milvus on IBM watsonx.data is always `ibmlhapikey`.
The password for Milvus on IBM watsonx.data is in the form of an IBM Cloud user API key.
[Get the user API key](https://cloud.ibm.com/docs/account?topic=account-userapikey\&interface=ui).
* For Milvus local, you will need:
* A [Milvus instance](https://milvus.io/docs/install-overview.md).
* The [URI](https://milvus.io/api-reference/pymilvus/v2.4.x/MilvusClient/Client/MilvusClient.md) of the instance.
* The name of the [database](https://milvus.io/docs/manage_databases.md) in the instance.
* The name of the [collection](https://milvus.io/docs/manage-collections.md) in the database.
Note the collection requirements at the end of this section.
* The [username and password, or token](https://milvus.io/docs/authenticate.md) to access the instance.
All Milvus instances require the target collection to have a defined schema before Unstructured can write to the collection. The minimum viable
schema for Unstructured contains only the fields `element_id`, `embeddings`, and `record_id`, as follows. This example code demonstrates the use of the
[Python SDK for Milvus](https://pypi.org/project/pymilvus/) to create a collection with this minimum viable schema,
targeting Milvus on IBM watsonx.data. For the `connections.connect` arguments to connect to other types of Milvus deployments, see your Milvus provider's documentation:
```python Python theme={null}
import os
from pymilvus import (
connections,
FieldSchema,
DataType,
CollectionSchema,
Collection,
)
connections.connect(
alias="default",
host=os.getenv("MILVUS_GRPC_HOST"),
port=os.getenv("MILVUS_GRPC_PORT"),
user=os.getenv("MILVUS_USER"),
password=os.getenv("MILVUS_PASSWORD"),
secure=True
)
primary_key = FieldSchema(
name="element_id",
dtype=DataType.VARCHAR,
is_primary=True,
max_length=200
)
vector = FieldSchema(
name="embeddings",
dtype=DataType.FLOAT_VECTOR,
dim=3072
)
record_id = FieldSchema(
name="record_id",
dtype=DataType.VARCHAR,
max_length=200
)
schema = CollectionSchema(
fields=[primary_key, vector, record_id],
enable_dynamic_field=True
)
collection = Collection(
name="my_collection",
schema=schema,
using="default"
)
index_params = {
"metric_type": "L2",
"index_type": "IVF_FLAT",
"params": {"nlist": 1024}
}
collection.create_index(
field_name="embeddings",
index_params=index_params
)
```
Other approaches, such as [creating collections instantly](https://milvus.io/docs/create-collection-instantly.md) or
[setting nullable and default fields](https://milvus.io/docs/nullable-and-default.md), have not
been fully evaluated by Unstructured and might produce unexpected results.
Unstructured cannot provide a schema that is guaranteed to work in all
circumstances. This is because these schemas will vary based on your source files' types; how you
want Unstructured to partition, chunk, and generate embeddings; any custom post-processing code that you run; and other factors.
The Milvus connector dependencies:
```bash CLI, Python theme={null}
pip install "unstructured-ingest[milvus]"
```
You might also need to install additional dependencies, depending on your needs. [Learn more](/ingestion/ingest-dependencies).
The following environment variables:
* `MILVUS_URI` - The Milvus instance's URI, represented by `--uri` (CLI) or `uri` (Python).
* `MILVUS_USER` and `MILVUS_PASSWORD`, or `MILVUS_TOKEN` - The username and password, or token, to access the instance. This is represented by `--user` and `--password`, or `--token` (CLI); or `user` and `password`, or `token` (Python).
* `MILVUS_DB` - The database's name, represented by `--db-name` (CLI) or `db_name` (Python).
* `MILVUS_COLLECTION` - The collection's name, represented by `--collection-name` (CLI) or `collection_name` (Python).
* `MILVUS_FIELDS_TO_INCLUDE` - A list of fields to include a comma-separated list (CLI) or an array of strings (Python), represented by `--field-to-include` (CLI) or `fields_to_include` (Python).
Additional settings include:
* To emit the `metadata` field's child fields directly into the output, include `--flatten-metadata` (CLI) or `flatten_metadata=True` (Python). This is the default if not specified.
* To keep the `metadata` field with its child fields intact in the output, include `--no-flatten-metadata` (CLI) or `flatten_metadata=False` (Python).
Now call the Unstructured CLI or Python. The source connector can be any of the ones supported. This example uses the local source connector:
This example sends files to Unstructured for processing by default. To process files locally instead, see the instructions at the end of this page.
```bash CLI theme={null}
#!/usr/bin/env bash
# Chunking and embedding are optional.
unstructured-ingest \
local \
--input-path $LOCAL_FILE_INPUT_DIR \
--chunking-strategy by_title \
--embedding-provider huggingface \
--partition-by-api \
--api-key $UNSTRUCTURED_API_KEY \
--partition-endpoint $UNSTRUCTURED_API_URL \
--strategy hi_res \
--additional-partition-args="{\"split_pdf_page\":\"true\", \"split_pdf_allow_failed\":\"true\", \"split_pdf_concurrency_level\": 15}" \
milvus \
--uri $MILVUS_URI \
--user $MILVUS_USER \
--password $MILVUS_PASSWORD \
--db-name $MILVUS_DB \
--collection-name $MILVUS_COLLECTION \
--fields-to-include type,element_id,text,embeddings
```
```python Python Ingest theme={null}
import os
from unstructured_ingest.pipeline.pipeline import Pipeline
from unstructured_ingest.interfaces import ProcessorConfig
from unstructured_ingest.processes.connectors.milvus import (
MilvusConnectionConfig,
MilvusAccessConfig,
MilvusUploadStagerConfig,
MilvusUploaderConfig
)
from unstructured_ingest.processes.connectors.local import (
LocalIndexerConfig,
LocalDownloaderConfig,
LocalConnectionConfig
)
from unstructured_ingest.processes.partitioner import PartitionerConfig
from unstructured_ingest.processes.chunker import ChunkerConfig
from unstructured_ingest.processes.embedder import EmbedderConfig
# Chunking and embedding are optional.
if __name__ == "__main__":
Pipeline.from_configs(
context=ProcessorConfig(),
indexer_config=LocalIndexerConfig(input_path=os.getenv("LOCAL_FILE_INPUT_DIR")),
downloader_config=LocalDownloaderConfig(),
source_connection_config=LocalConnectionConfig(),
partitioner_config=PartitionerConfig(
partition_by_api=True,
api_key=os.getenv("UNSTRUCTURED_API_KEY"),
partition_endpoint=os.getenv("UNSTRUCTURED_API_URL"),
strategy="hi_res",
additional_partition_args={
"split_pdf_page": True,
"split_pdf_allow_failed": True,
"split_pdf_concurrency_level": 15
}
),
chunker_config=ChunkerConfig(chunking_strategy="by_title"),
embedder_config=EmbedderConfig(embedding_provider="huggingface"),
destination_connection_config=MilvusConnectionConfig(
access_config=MilvusAccessConfig(
password=os.getenv("MILVUS_PASSWORD")
),
uri=os.getenv("MILVUS_URI"),
user=os.getenv("MILVUS_USER"),
db_name=os.getenv("MILVUS_DB")
),
stager_config=MilvusUploadStagerConfig(fields_to_include=["type", "element_id", "text", "embeddings"]),
uploader_config=MilvusUploaderConfig(collection_name=os.getenv("MILVUS_COLLECTION"))
).run()
```
For the Unstructured Ingest CLI and the Unstructured Ingest Python library, you can use the `--partition-by-api` option (CLI) or `partition_by_api` (Python) parameter to specify where files are processed:
* To do local file processing, omit `--partition-by-api` (CLI) or `partition_by_api` (Python), or explicitly specify `partition_by_api=False` (Python).
Local file processing does not use an Unstructured API key or API URL, so you can also omit the following, if they appear:
* `--api-key $UNSTRUCTURED_API_KEY` (CLI) or `api_key=os.getenv("UNSTRUCTURED_API_KEY")` (Python)
* `--partition-endpoint $UNSTRUCTURED_API_URL` (CLI) or `partition_endpoint=os.getenv("UNSTRUCTURED_API_URL")` (Python)
* The environment variables `UNSTRUCTURED_API_KEY` and `UNSTRUCTURED_API_URL`
* To send files to the [Unstructured Partition Endpoint](/api-reference/partition/overview) for processing, specify `--partition-by-api` (CLI) or `partition_by_api=True` (Python).
Unstructured also requires an Unstructured API key and API URL, by adding the following:
* `--api-key $UNSTRUCTURED_API_KEY` (CLI) or `api_key=os.getenv("UNSTRUCTURED_API_KEY")` (Python)
* `--partition-endpoint $UNSTRUCTURED_API_URL` (CLI) or `partition_endpoint=os.getenv("UNSTRUCTURED_API_URL")` (Python)
* The environment variables `UNSTRUCTURED_API_KEY` and `UNSTRUCTURED_API_URL`, representing your API key and API URL, respectively.
You must specify the API URL only if you are not using the default API URL for Unstructured Ingest, for example, if you are using a version of the Unstructured API that is hosted on your own compute infrastructure.
The default API URL for Unstructured Ingest is `https://api.unstructuredapp.io/general/v0/general`, which is the API URL for the [Unstructured Partition Endpoint](/api-reference/partition/overview).
If you do not have an API key, [get one now](/api-reference/partition/overview).
If the Unstructured API is hosted on your own compute infrastructure, the process
for generating Unstructured API keys, and the Unstructured API URL that you use, are different.
For details, contact Unstructured Sales at
[sales@unstructured.io](mailto:sales@unstructured.io).