Ingest dependencies - Unstructured

When you install the Unstructured Ingest CLI and the Unstructured Ingest Python library by running the command pip install unstructured-ingest by itself, you get the following by default:

The local source connector and the local destination connector.
Support for the following file types:

File type
`.bmp`
`.eml`
`.heic`
`.html`
`.jpg`
`.jpeg`
`.tiff`
`.png`
`.txt`
`.xml`

To add support for additional file types, run the following:

Command	File type
`pip install "unstructured-ingest[csv]"`	`.csv`
`pip install "unstructured-ingest[doc]"`	`.doc`
`pip install "unstructured-ingest[docx]"`	`.docx`
`pip install "unstructured-ingest[epub]"`	`.epub`
`pip install "unstructured-ingest[md]"`	`.md`
`pip install "unstructured-ingest[msg]"`	`.msg`
`pip install "unstructured-ingest[odt]"`	`.odt`
`pip install "unstructured-ingest[org]"`	`.org`
`pip install "unstructured-ingest[pdf]"`	`.pdf`
`pip install "unstructured-ingest[ppt]"`	`.ppt`
`pip install "unstructured-ingest[pptx]"`	`.pptx`
`pip install "unstructured-ingest[rtf]"`	`.rtf`
`pip install "unstructured-ingest[rst]"`	`.rst`
`pip install "unstructured-ingest[tsv]"`	`.tsv`
`pip install "unstructured-ingest[xlsx]"`	`.xlsx`

To add support for additional connectors, run the following:

Command	Connector type
`pip install "unstructured-ingest[airtable]"`	Airtable
`pip install "unstructured-ingest[astra]"`	Astra DB
`pip install "unstructured-ingest[azure]"`	Azure Blob Storage
`pip install "unstructured-ingest[azure-ai-search]"`	Azure AI Search
`pip install "unstructured-ingest[box]"`	Box
`pip install "unstructured-ingest[chroma]"`	Chroma
`pip install "unstructured-ingest[confluence]"`	Confluence
`pip install "unstructured-ingest[couchbase]"`	Couchbase
`pip install "unstructured-ingest[databricks-volumes]"`	Databricks Volumes
`pip install "unstructured-ingest[delta-table]"`	Delta Tables
`pip install "unstructured-ingest[dropbox]"`	Dropbox
`pip install "unstructured-ingest[dropbox]"`	DuckDB, MotherDuck
`pip install "unstructured-ingest[elasticsearch]"`	Elasticsearch
`pip install "unstructured-ingest[gcs]"`	Google Cloud Storage
`pip install "unstructured-ingest[github]"`	GitHub
`pip install "unstructured-ingest[gitlab]"`	GitLab
`pip install "unstructured-ingest[google-drive]"`	Google Drive
`pip install "unstructured-ingest[jira]"`	JIRA
`pip install "unstructured-ingest[kafka]"`	Apache Kafka
`pip install "unstructured-ingest[milvus]"`	Milvus
`pip install "unstructured-ingest[mongodb]"`	MongoDB
`pip install "unstructured-ingest[neo4j]"`	Neo4j
`pip install "unstructured-ingest[notion]"`	Notion
`pip install "unstructured-ingest[onedrive]"`	OneDrive
`pip install "unstructured-ingest[opensearch]"`	OpenSearch
`pip install "unstructured-ingest[outlook]"`	Outlook
`pip install "unstructured-ingest[pinecone]"`	Pinecone
`pip install "unstructured-ingest[postgres]"`	PostgreSQL, SQLite
`pip install "unstructured-ingest[qdrant]"`	Qdrant
`pip install "unstructured-ingest[redis]"`	Redis
`pip install "unstructured-ingest[s3]"`	Amazon S3
`pip install "unstructured-ingest[sharepoint]"`	SharePoint
`pip install "unstructured-ingest[salesforce]"`	Salesforce
`pip install "unstructured-ingest[singlestore]"`	SingleStore
`pip install "unstructured-ingest[snowflake]"`	Snowflake
`pip install "unstructured-ingest[sftp]"`	SFTP
`pip install "unstructured-ingest[slack]"`	Slack
`pip install "unstructured-ingest[vectara]"`	Vectara
`pip install "unstructured-ingest[weaviate]"`	Weaviate

To add support for available embedding libraries, run the following:

Command	Embedding library type
`pip install "unstructured-ingest[bedrock]"`	Amazon Bedrock
`pip install "unstructured-ingest[embed-huggingface]"`	Hugging Face
`pip install "unstructured-ingest[embed-octoai]"`	OctoAI
`pip install "unstructured-ingest[embed-vertexai]"`	Google Vertex AI
`pip install "unstructured-ingest[embed-voyageai]"`	Voyage AI
`pip install "unstructured-ingest[embed-mixedbreadai]"`	Mixedbread
`pip install "unstructured-ingest[openai]"`	OpenAI, Azure OpenAI
`pip install "unstructured-ingest[togetherai]"`	together.ai

For details about the specific dependencies that are installed, see: