jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

[Docs] - Cleanup Components Folder (#1852)

Browse source 
* inputs

* agents

* chains

* custom-component

* align-admonitions-in-custom

* data-and-embeddings

* experimental

* helpers

* memories

* model_specs

* outputs

* prompts

* retrievers

* textsplitter

* tools

* utilities

* vector-stores
This commit is contained in:
Mendon Kissling 2024-05-07 17:39:40 -04:00 • committed by GitHub
commit ba59f077a2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 862 additions and 1398 deletions
Download patch file Download diff file Expand all files Collapse all files

674
docs/docs/components/vector-stores.mdx
View file

@ -1,119 +1,77 @@
import Admonition from "@theme/Admonition";
# Vector Stores
# Vector Stores Documentation
### Astra DB
The `Astra DB` is a component for initializing an Astra DB Vector Store from Records. It facilitates the creation of Astra DB-based vector indexes for efficient document storage and retrieval.
The `Astra DB` initializes a vector store using Astra DB from records. It creates Astra DB-based vector indexes to efficiently store and retrieve documents.
**Params**
**Parameters:**
- **Input:** The input documents or records.
- **Embedding:** The embedding model used by Astra DB.
- **Collection Name:** The name of the collection in Astra DB.
- **Token:** The token for Astra DB.
- **API Endpoint:** The API endpoint for Astra DB.
- **Namespace:** The namespace in Astra DB.
- **Metric:** The metric to use in Astra DB.
- **Batch Size:** The batch size for Astra DB.
- **Bulk Insert Batch Concurrency:** The bulk insert batch concurrency for Astra DB.
- **Bulk Insert Overwrite Concurrency:** The bulk insert overwrite concurrency for Astra DB.
- **Bulk Delete Concurrency:** The bulk delete concurrency for Astra DB.
- **Setup Mode:** The setup mode for the vector store.
- **Pre Delete Collection:** Pre delete collection.
- **Metadata Indexing Include:** Metadata indexing include.
- **Metadata Indexing Exclude:** Metadata indexing exclude.
- **Collection Indexing Policy:** Collection indexing policy.
- **Input:** Documents or records for input.
- **Embedding:** Embedding model Astra DB uses.
- **Collection Name:** Name of the Astra DB collection.
- **Token:** Authentication token for Astra DB.
- **API Endpoint:** API endpoint for Astra DB.
- **Namespace:** Astra DB namespace.
- **Metric:** Metric used by Astra DB.
- **Batch Size:** Batch size for operations.
- **Bulk Insert Batch Concurrency:** Concurrency level for bulk inserts.
- **Bulk Insert Overwrite Concurrency:** Concurrency level for overwriting during bulk inserts.
- **Bulk Delete Concurrency:** Concurrency level for bulk deletions.
- **Setup Mode:** Setup mode for the vector store.
- **Pre Delete Collection:** Option to delete the collection before setup.
- **Metadata Indexing Include:** Fields to include in metadata indexing.
- **Metadata Indexing Exclude:** Fields to exclude from metadata indexing.
- **Collection Indexing Policy:** Indexing policy for the collection.
<Admonition type="note" title="Note">
<p>
Ensure that the required Astra DB token and API endpoint are properly configured.
</p>
Ensure you configure the necessary Astra DB token and API endpoint before starting.
</Admonition>
---
### Astra DB Search
The `Astra DBSearch` is a component for searching an existing Astra DB Vector Store for similar documents. It extends the functionality of the `Astra DB` component to provide efficient document retrieval based on similarity metrics.
`Astra DBSearch` searches an existing Astra DB vector store for documents similar to the input. It uses the `Astra DB` component's functionality for efficient retrieval.
**Params**
**Parameters:**
- **Search Type:** The type of search to perform (e.g., Similarity, MMR).
- **Input Value:** The input value to search for.
- **Embedding:** The embedding model used by Astra DB.
- **Collection Name:** The name of the collection in Astra DB.
- **Token:** The token for Astra DB.
- **API Endpoint:** The API endpoint for Astra DB.
- **Namespace:** The namespace in Astra DB.
- **Metric:** The metric to use in Astra DB.
- **Batch Size:** The batch size for Astra DB.
- **Bulk Insert Batch Concurrency:** The bulk insert batch concurrency for Astra DB.
- **Bulk Insert Overwrite Concurrency:** The bulk insert overwrite concurrency for Astra DB.
- **Bulk Delete Concurrency:** The bulk delete concurrency for Astra DB.
- **Setup Mode:** The setup mode for the vector store.
- **Pre Delete Collection:** Pre delete collection.
- **Metadata Indexing Include:** Metadata indexing include.
- **Metadata Indexing Exclude:** Metadata indexing exclude.
- **Collection Indexing Policy:** Collection indexing policy.
- **Search Type:** Type of search, such as Similarity or MMR.
- **Input Value:** Value to search for.
- **Embedding:** Embedding model Astra DB uses.
- **Collection Name:** Name of the Astra DB collection.
- **Token:** Authentication token for Astra DB.
- **API Endpoint:** API endpoint for Astra DB.
- **Namespace:** Astra DB namespace.
- **Metric:** Metric used by Astra DB.
- **Batch Size:** Batch size for operations.
- **Bulk Insert Batch Concurrency:** Concurrency level for bulk inserts.
- **Bulk Insert Overwrite Concurrency:** Concurrency level for overwriting during bulk inserts.
- **Bulk Delete Concurrency:** Concurrency level for bulk deletions.
- **Setup Mode:** Setup mode for the vector store.
- **Pre Delete Collection:** Option to delete the collection before setup.
- **Metadata Indexing Include:** Fields to include in metadata indexing.
- **Metadata Indexing Exclude:** Fields to exclude from metadata indexing.
- **Collection Indexing Policy:** Indexing policy for the collection.
---
### Chroma
The `Chroma` is a component designed for implementing a Vector Store using Chroma. This component allows users to utilize Chroma for efficient vector storage and retrieval within their language processing workflows.
`Chroma` sets up a vector store using Chroma for efficient vector storage and retrieval within language processing workflows.
**Params**
- **Collection Name:** The name of the collection.
- **Persist Directory:** The directory to persist the Vector Store to.
- **Server CORS Allow Origins (Optional):** The CORS allow origins for the Chroma server.
- **Server Host (Optional):** The host for the Chroma server.
- **Server Port (Optional):** The port for the Chroma server.
- **Server gRPC Port (Optional):** The gRPC port for the Chroma server.
- **Server SSL Enabled (Optional):** Whether to enable SSL for the Chroma server.
**Parameters:**
- **Collection Name:** Name of the collection.
- **Persist Directory:** Directory to persist the Vector Store.
- **Server CORS Allow Origins (Optional):** CORS allow origins for the Chroma server.
- **Server Host (Optional):** Host for the Chroma server.
- **Server Port (Optional):** Port for the Chroma server.
- **Server gRPC Port (Optional):** gRPC port for the Chroma server.
- **Server SSL Enabled (Optional):** SSL configuration for the Chroma server.
- **Input:** Input data for creating the Vector Store.
- **Embedding:** The embeddings to use for the Vector Store.
- **Embedding:** Embeddings used for the Vector Store.
For detailed documentation and integration guides, please refer to the [Chroma Component Documentation](https://python.langchain.com/docs/integrations/vectorstores/chroma).
@ -121,515 +79,335 @@ For detailed documentation and integration guides, please refer to the [Chroma C
### Chroma Search
The `ChromaSearch` is a component designed for searching a Chroma collection for similar documents. This component integrates with Chroma to facilitate efficient document retrieval based on similarity metrics.
`ChromaSearch` searches a Chroma collection for documents similar to the input text. It leverages Chroma to ensure efficient document retrieval.
**Params**
**Parameters:**
- **Input:** The input text to search for similar documents.
- **Search Type:** The type of search to perform ("Similarity" or "MMR").
- **Collection Name:** The name of the Chroma collection.
- **Index Directory:** The directory where the Chroma index is stored.
- **Embedding:** The embedding model used to vectorize inputs (make sure to use the same as the index).
- **Server CORS Allow Origins (Optional):** The CORS allow origins for the Chroma server.
- **Server Host (Optional):** The host for the Chroma server.
- **Server Port (Optional):** The port for the Chroma server.
- **Server gRPC Port (Optional):** The gRPC port for the Chroma server.
- **Server SSL Enabled (Optional):** Whether SSL is enabled for the Chroma server.
- **Input:** Input text for search.
- **Search Type:** Type of search, such as Similarity or MMR.
- **Collection Name:** Name of the Chroma collection.
- **Index Directory:** Directory where the Chroma index is stored.
- **Embedding:** Embedding model used for vectorization.
- **Server CORS Allow Origins (Optional):** CORS allow origins for the Chroma server.
- **Server Host (Optional):** Host for the Chroma server.
- **Server Port (Optional):** Port for the Chroma server.
- **Server gRPC Port (Optional):** gRPC port for the Chroma server.
- **Server SSL Enabled (Optional):** SSL configuration for the Chroma server.
---
### FAISS
The `FAISS` is a component designed for ingesting documents into a FAISS Vector Store. It facilitates efficient document indexing and retrieval using the FAISS library.
The `FAISS` component manages document ingestion into a FAISS Vector Store, optimizing document indexing and retrieval.
**Params**
**Parameters:**
- **Embedding:** The embedding model used to vectorize inputs.
- **Embedding:** Model used for vectorizing inputs.
- **Input:** Documents to ingest.
- **Folder Path:** Save path for the FAISS index, relative to Langflow.
- **Index Name:** Index identifier.
- **Input:** The input documents to ingest into the FAISS Vector Store.
- **Folder Path:** The path to save the FAISS index. It will be relative to where Langflow is running.
- **Index Name:** The name of the FAISS index.
For detailed documentation and integration guides, please refer to the [FAISS Component Documentation](https://faiss.ai/index.html).
For more details, see the [FAISS Component Documentation](https://faiss.ai/index.html).
---
### FAISS Search
The `FAISSSearch` is a component for searching a FAISS Vector Store for similar documents. It enables efficient document retrieval based on similarity metrics using FAISS.
`FAISSSearch` searches a FAISS Vector Store for documents similar to a given input, using similarity metrics for efficient retrieval.
**Params**
**Parameters:**
- **Embedding:** The embedding model used by the FAISS Vector Store.
- **Folder Path:** The path from which to load the FAISS index. It will be relative to where Langflow is running.
- **Input:** The input value to search for similar documents.
- **Index Name:** The name of the FAISS index.
- **Embedding:** Model used in the FAISS Vector Store.
- **Folder Path:** Path to load the FAISS index from, relative to Langflow.
- **Input:** Search query.
- **Index Name:** Index identifier.
---
### MongoDB Atlas
The `MongoDBAtlas` is a component used to construct a MongoDB Atlas Vector Search vector store from Records. It facilitates the creation of MongoDB Atlas-based vector stores for efficient document storage and retrieval.
`MongoDBAtlas` builds a MongoDB Atlas-based vector store from records, streamlining the storage and retrieval of documents.
**Params**
**Parameters:**
- **Embedding:** The embedding model used by the MongoDB Atlas Vector Search.
- **Input:** The input documents or records.
- **Collection Name:** The name of the collection in the MongoDB Atlas database.
- **Database Name:** The name of the database in MongoDB Atlas.
- **Index Name:** The name of the index in MongoDB Atlas.
- **MongoDB Atlas Cluster URI:** The URI of the MongoDB Atlas cluster.
- **Search Kwargs:** Additional search arguments for MongoDB Atlas.
- **Embedding:** Model used by MongoDB Atlas.
- **Input:** Documents or records.
- **Collection Name:** Collection identifier in MongoDB Atlas.
- **Database Name:** Database identifier.
- **Index Name:** Index identifier.
- **MongoDB Atlas Cluster URI:** Cluster URI.
- **Search Kwargs:** Additional search parameters.
<Admonition type="note" title="Note">
<p>Ensure that pymongo is installed to use MongoDB Atlas Vector Store.</p>
Ensure pymongo is installed for using MongoDB Atlas Vector Store.
</Admonition>
---
### MongoDB Atlas Search
The `MongoDBAtlasSearch` is a component for searching a MongoDB Atlas Vector Store for similar documents. It extends the functionality of the MongoDBAtlasComponent to provide efficient document retrieval based on similarity metrics.
`MongoDBAtlasSearch` leverages the MongoDBAtlas component to search for documents based on similarity metrics.
**Params**
**Parameters:**
- **Search Type:** The type of search to perform. Options: "Similarity", "MMR".
- **Input:** The input value to search for.
- **Embedding:** The embedding model used by the MongoDB Atlas Vector Store.
- **Collection Name:** The name of the collection in the MongoDB Atlas database.
- **Database Name:** The name of the database in MongoDB Atlas.
- **Index Name:** The name of the index in MongoDB Atlas.
- **MongoDB Atlas Cluster URI:** The URI of the MongoDB Atlas cluster.
- **Search Kwargs:** Additional search arguments for MongoDB Atlas.
- **Search Type:** Type of search, such as "Similarity" or "MMR".
- **Input:** Search query.
- **Embedding:** Model used in the Vector Store.
- **Collection Name:** Collection identifier.
- **Database Name:** Database identifier.
- **Index Name:** Index identifier.
- **MongoDB Atlas Cluster URI:** Cluster URI.
- **Search Kwargs:** Additional search parameters.
---
### PGVector
The `PGVector` is a component for implementing a Vector Store using PostgreSQL. It allows users to store and retrieve vectors efficiently within a PostgreSQL database.
`PGVector` integrates a Vector Store within a PostgreSQL database, allowing efficient storage and retrieval of vectors.
**Params**
**Parameters:**
- **Input:** The input value to use for the Vector Store.
- **Input:** Value for the Vector Store.
- **Embedding:** Model used.
- **PostgreSQL Server Connection String:** Server URL.
- **Table:** Table name in the PostgreSQL database.
- **Embedding:** The embedding model used by the Vector Store.
- **PostgreSQL Server Connection String:** The URL for the PostgreSQL server.
- **Table:** The name of the table in the PostgreSQL database.
For detailed documentation and integration guides, please refer to the [PGVector Component Documentation](https://python.langchain.com/docs/integrations/vectorstores/pgvector).
For more details, see the [PGVector Component Documentation](https://python.langchain.com/docs/integrations/vectorstores/pgvector).
<Admonition type="note" title="Note">
<p>
Ensure that the required PostgreSQL server is accessible and properly
configured.
</p>
Ensure the PostgreSQL server is accessible and configured correctly.
</Admonition>
---
### PGVector Search
The `PGVectorSearch` is a component for searching a PGVector Store for similar documents. It extends the functionality of the PGVectorComponent to provide efficient document retrieval based on similarity metrics.
`PGVectorSearch` extends `PGVector` to search for documents based on similarity metrics.
**Params**
**Parameters:**
- **Input:** The input value to search for.
- **Embedding:** The embedding model used by the Vector Store.
- **PostgreSQL Server Connection String:** The URL for the PostgreSQL server.
- **Table:** The name of the table in the PostgreSQL database.
- **Search Type:** The type of search to perform (e.g., "Similarity", "MMR").
- **Input:** Search query.
- **Embedding:** Model used.
- **PostgreSQL Server Connection String:** Server URL.
- **Table:** Table name.
- **Search Type:** Type of search, such as "Similarity" or "MMR".
---
### Pinecone
The `Pinecone` is a component used to construct a Pinecone wrapper from Records. It facilitates the creation of Pinecone-based vector indexes for efficient document storage and retrieval.
`Pinecone` constructs a Pinecone wrapper from records, setting up Pinecone-based vector indexes for document storage and retrieval.
**Params**
**Parameters:**
- **Input:** The input documents or records.
- **Embedding:** The embedding model used by Pinecone.
- **Index Name:** The name of the index in Pinecone.
- **Namespace:** The namespace in Pinecone.
- **Pinecone API Key:** The API key for Pinecone.
- **Pinecone Environment:** The environment for Pinecone.
- **Search Kwargs:** Additional search keyword arguments for Pinecone.
- **Pool Threads:** The number of threads to use for Pinecone.
- **Input:** Documents or records.
- **Embedding:** Model used.
- **Index Name:** Index identifier.
- **Namespace:** Namespace used.
- **Pinecone API Key:** API key.
- **Pinecone Environment:** Environment settings.
- **Search Kwargs:** Additional search parameters.
- **Pool Threads:** Number of threads.
<Admonition type="note" title="Note">
<p>
Ensure that the required Pinecone API key and environment are properly
configured.
</p>
Ensure the Pinecone API key and environment are correctly configured.
</Admonition>
---
### Pinecone Search
The `PineconeSearch` is a component used to search a Pinecone Vector Store for similar documents. It extends the functionality of the `PineconeComponent` to provide efficient document retrieval based on similarity metrics.
`PineconeSearch` searches a Pinecone Vector Store for documents similar to the input, using advanced similarity metrics.
**Params**
**Parameters:**
- **Search Type:** The type of search to perform (e.g., Similarity, MMR).
- **Input Value:** The input value to search for.
- **Embedding:** The embedding model used by Pinecone.
- **Index Name:** The name of the index in Pinecone.
- **Namespace:** The namespace in Pinecone.
- **Pinecone API Key:** The API key for Pinecone.
- **Pinecone Environment:** The environment for Pinecone.
- **Search Kwargs:** Additional search keyword arguments for Pinecone.
- **Pool Threads:** The number of threads to use for Pinecone.
- **Search Type:** Type of search, such as "Similarity" or "MMR".
- **Input Value:** Search query.
- **Embedding:** Model used.
- **Index Name:** Index identifier.
- **Namespace:** Namespace used.
- **Pinecone API Key:** API key.
- **Pinecone Environment:** Environment settings.
- **Search Kwargs:** Additional search parameters.
- **Pool Threads:** Number of threads.
---
### Qdrant
The `Qdrant` is a component used to construct a Qdrant wrapper from a list of texts. It allows for efficient similarity search and retrieval operations based on the provided embeddings.
`Qdrant` allows efficient similarity searches and retrieval operations, using a list of texts to construct a Qdrant wrapper.
**Params**
**Parameters:**
- **Input:** The input documents or records.
- **Embedding:** The embedding model used by Qdrant.
- **API Key:** The API key for Qdrant (password field).
- **Collection Name:** The name of the collection in Qdrant.
- **Content Payload Key:** The key for the content payload in the documents (advanced).
- **Distance Function:** The distance function to use in Qdrant (advanced).
- **gRPC Port:** The gRPC port for Qdrant (advanced).
- **Host:** The host for Qdrant (advanced).
- **HTTPS:** Enable HTTPS for Qdrant (advanced).
- **Location:** The location for Qdrant (advanced).
- **Metadata Payload Key:** The key for the metadata payload in the documents (advanced).
- **Path:** The path for Qdrant (advanced).
- **Port:** The port for Qdrant (advanced).
- **Prefer gRPC:** Prefer gRPC for Qdrant (advanced).
- **Prefix:** The prefix for Qdrant (advanced).
- **Search Kwargs:** Additional search keyword arguments for Qdrant (advanced).
- **Timeout:** The timeout for Qdrant (advanced).
- **URL:** The URL for Qdrant (advanced).
- **Input:** Documents or records.
- **Embedding:** Model used.
- **API Key:** Qdrant API key.
- **Collection Name:** Collection identifier.
- **Advanced Settings:** Includes content payload key, distance function, gRPC port, host, HTTPS, location, metadata payload key, path, port, prefer gRPC, prefix, search kwargs, timeout, URL.
---
### Qdrant Search
The `QdrantSearch` is a component used to search a Qdrant Vector Store for similar documents. It extends the functionality of the `QdrantComponent` to provide efficient document retrieval based on similarity metrics.
`QdrantSearch` extends `Qdrant` to search for documents similar to the input based on advanced similarity metrics.
**Params**
**Parameters:**
- **Search Type:** The type of search to perform (e.g., Similarity, MMR).
- **Input Value:** The input value to search for.
- **Embedding:** The embedding model used by Qdrant.
- **API Key:** The API key for Qdrant (password field).
- **Collection Name:** The name of the collection in Qdrant.
- **Content Payload Key:** The key for the content payload in the documents (advanced).
- **Distance Function:** The distance function to use in Qdrant (advanced).
- **gRPC Port:** The gRPC port for Qdrant (advanced).
- **Host:** The host for Qdrant (advanced).
- **HTTPS:** Enable HTTPS for Qdrant (advanced).
- **Location:** The location for Qdrant (advanced).
- **Metadata Payload Key:** The key for the metadata payload in the documents (advanced).
- **Path:** The path for Qdrant (advanced).
- **Port:** The port for Qdrant (advanced).
- **Prefer gRPC:** Prefer gRPC for Qdrant (advanced).
- **Prefix:** The prefix for Qdrant (advanced).
- **Search Kwargs:** Additional search keyword arguments for Qdrant (advanced).
- **Timeout:** The timeout for Qdrant (advanced).
- **URL:** The URL for Qdrant (advanced).
- **Search Type:** Type of search, such as "Similarity" or "MMR".
- **Input Value:** Search query.
- **Embedding:** Model used.
- **API Key:** Qdrant API key.
- **Collection Name:** Collection identifier.
- **Advanced Settings:** Includes content payload key, distance function, gRPC port, host, HTTPS, location, metadata payload key, path, port, prefer gRPC, prefix, search kwargs, timeout, URL.
---
### Redis
The `Redis` is a component for implementing a Vector Store using Redis. It provides functionality to store and retrieve vectors efficiently from a Redis database.
`Redis` manages a Vector Store in a Redis database, supporting efficient vector storage and retrieval.
**Params**
**Parameters:**
- **Index Name:** The name of the index in Redis (default: your_index).
- **Index Name:** Default index name.
- **Input:** Data for building the Redis Vector Store.
- **Embedding:** Model used.
- **Schema:** Optional schema file (.yaml) for document structure.
- **Redis Server Connection String:** Server URL.
- **Redis Index:** Optional index name.
- **Input:** The input data to build the Redis Vector Store (input types: Document, Record).
- **Embedding:** The embedding model used by Redis.
- **Schema:** The schema file (.yaml) to define the structure of the documents (optional).
- **Redis Server Connection String:** The connection string for the Redis server.
- **Redis Index:** The name of the Redis index (optional).
For detailed documentation, please refer to the [Redis Documentation](https://python.langchain.com/docs/integrations/vectorstores/redis).
For detailed documentation, refer to the [Redis Documentation](https://python.langchain.com/docs/integrations/vectorstores/redis).
<Admonition type="note" title="Note">
<p>
Ensure that the required Redis server connection URL and index name are
properly configured. If no documents are provided, a schema must be
provided.
</p>
Ensure the Redis server URL and index name are configured correctly. Provide a schema if no documents are available.
</Admonition>
---
### Redis Search
The `RedisSearch` is a component for searching a Redis Vector Store for similar documents.
`RedisSearch` searches a Redis Vector Store for documents similar to the input.
**Params**
**Parameters:**
- **Search Type:** The type of search to perform (e.g., Similarity, MMR).
- **Input Value:** The input value to search for.
- **Index Name:** The name of the index in Redis (default: your_index).
- **Embedding:** The embedding model used by Redis.
- **Schema:** The schema file (.yaml) to define the structure of the documents (optional).
- **Redis Server Connection String:** The connection string for the Redis server.
- **Redis Index:** The name of the Redis index (optional).
- **Search Type:** Type of search, such as "Similarity" or "MMR".
- **Input Value:** Search query.
- **Index Name:** Default index name.
- **Embedding:** Model used.
- **Schema:** Optional schema file (.yaml) for document structure.
- **Redis Server Connection String:** Server URL.
- **Redis Index:** Optional index name.
---
### Supabase
The `Supabase` is a component for initializing a Supabase Vector Store from texts and embeddings.
`Supabase` initializes a Supabase Vector Store from texts and embeddings, setting up an environment for efficient document retrieval.
**Params**
**Parameters:**
- **Input:** The input documents or records.
- **Embedding:** The embedding model used by Supabase.
- **Query Name:** The name of the query (optional).
- **Search Kwargs:** Additional search keyword arguments for Supabase (advanced).
- **Supabase Service Key:** The service key for Supabase.
- **Supabase URL:** The URL for the Supabase instance.
- **Table Name:** The name of the table in Supabase (advanced).
- **Input:** Documents or records.
- **Embedding:** Model used.
- **Query Name:** Optional query name.
- **Search Kwargs:** Advanced search parameters.
- **Supabase Service Key:** Service key.
- **Supabase URL:** Instance URL.
- **Table Name:** Optional table name.
<Admonition type="note" title="Note">
<p>
Ensure that the required Supabase service key, Supabase URL, and table name
are properly configured.
</p>
Ensure the Supabase service key, URL, and table name are properly configured.
</Admonition>
---
### Supabase Search
The `SupabaseSearch` is a component for searching a Supabase Vector Store for similar documents.
`SupabaseSearch` searches a Supabase Vector Store for documents similar to the input.
**Params**
**Parameters:**
- **Search Type:** The type of search to perform (e.g., Similarity, MMR).
- **Input Value:** The input value to search for.
- **Embedding:** The embedding model used by Supabase.
- **Query Name:** The name of the query (optional).
- **Search Kwargs:** Additional search keyword arguments for Supabase (advanced).
- **Supabase Service Key:** The service key for Supabase.
- **Supabase URL:** The URL for the Supabase instance.
- **Table Name:** The name of the table in Supabase (advanced).
- **Search Type:** Type of search, such as "Similarity" or "MMR".
- **Input Value:** Search query.
- **Embedding:** Model used.
- **Query Name:** Optional query name.
- **Search Kwargs:** Advanced search parameters.
- **Supabase Service Key:** Service key.
- **Supabase URL:** Instance URL.
- **Table Name:** Optional table name.
---
### Vectara
The `Vectara` is a component for implementing a Vector Store using Vectara.
`Vectara` sets up a Vectara Vector Store from files or upserted data, optimizing document retrieval.
**Params**
**Parameters:**
- **Vectara Customer ID:** The customer ID for Vectara.
- **Vectara Customer ID:** Customer ID.
- **Vectara Corpus ID:** Corpus ID.
- **Vectara API Key:** API key.
- **Files Url:** Optional URLs for file initialization.
- **Input:** Optional data for corpus upsert.
- **Vectara Corpus ID:** The corpus ID for Vectara.
- **Vectara API Key:** The API key for Vectara.
- **Files Url:** The URL(s) of the file(s) to be used for initializing the Vectara Vector Store (optional).
- **Input:** The input data to be upserted to the corpus (optional).
For detailed documentation and integration guides, please refer to the [Vectara Component Documentation](https://python.langchain.com/docs/integrations/vectorstores/vectara).
For more information, consult the [Vectara Component Documentation](https://python.langchain.com/docs/integrations/vectorstores/vectara).
<Admonition type="note" title="Note">
<p>
If `inputs` are provided, they will be upserted to the corpus. If
`files_url` are provided, Vectara will process the files from the URLs.
</p>
If inputs or files_url are provided, they will be processed accordingly.
</Admonition>
---
### Vectara Search
The `VectaraSearch` is a component for searching a Vectara Vector Store for similar documents.
`VectaraSearch` searches a Vectara Vector Store for documents based on the provided input.
**Params**
**Parameters:**
- **Search Type:** The type of search to perform (e.g., Similarity, MMR).
- **Input Value:** The input value to search for.
- **Vectara Customer ID:** The customer ID for Vectara.
- **Vectara Corpus ID:** The corpus ID for Vectara.
- **Vectara API Key:** The API key for Vectara.
- **Files Url:** The URL(s) of the file(s) to be used for initializing the Vectara Vector Store (optional).
- **Search Type:** Type of search, such as "Similarity" or "MMR".
- **Input Value:** Search query.
- **Vectara Customer ID:** Customer ID.
- **Vectara Corpus ID:** Corpus ID.
- **Vectara API Key:** API key.
- **Files Url:** Optional URLs for file initialization.
---
### Weaviate
The `Weaviate` is a component for implementing a Vector Store using Weaviate.
`Weaviate` facilitates a Weaviate Vector Store setup, optimizing text and document indexing and retrieval.
**Params**
**Parameters:**
- **Weaviate URL:** The URL of the Weaviate instance (default: http://localhost:8080).
- **Weaviate URL:** Default instance URL.
- **Search By Text:** Indicates whether to search by text.
- **API Key:** Optional API key for authentication.
- **Index Name:** Optional index name.
- **Text Key:** Default text extraction key.
- **Input:** Document or record.
- **Embedding:** Model used.
- **Attributes:** Optional additional attributes.
- **Search By Text:** Boolean indicating whether to search by text (default: False).
- **API Key:** The API key for authentication (optional).
- **Index name:** The name of the index in Weaviate (optional).
- **Text Key:** The key used to extract text from documents (default: "text").
- **Input:** The input document or record.
- **Embedding:** The embedding model used by Weaviate.
- **Attributes:** Additional attributes to consider during indexing (optional).
For detailed documentation and integration guides, please refer to the [Weaviate Component Documentation](https://python.langchain.com/docs/integrations/vectorstores/weaviate).
For more details, see the [Weaviate Component Documentation](https://python.langchain.com/docs/integrations/vectorstores/weaviate).
<Admonition type="note" title="Note">
<p>
Before using the Weaviate Vector Store component, ensure that you have a
Weaviate instance running and accessible at the specified URL. Additionally,
make sure to provide the correct API key for authentication if required.
Adjust the index name, text key, and attributes according to your dataset
and indexing requirements. Finally, ensure that the provided embeddings are
compatible with Weaviate's requirements.
</p>
Ensure Weaviate instance is running and accessible. Verify API key, index name, text key, and attributes are set correctly.
</Admonition>
---
### Weaviate Search
The `WeaviateSearch` component facilitates searching a Weaviate Vector Store for similar documents.
`WeaviateSearch` searches a Weaviate Vector Store for documents similar to the input.
**Params**
**Parameters:**
- **Search Type:** The type of search to perform (e.g., Similarity, MMR).
- **Search Type:** Type of search, such as "Similarity" or "MMR".
- **Input Value:** Search query.
- **Weaviate URL:** Default instance URL.
- **Search By Text:** Indicates whether to search by text.
- **API Key:** Optional API key for authentication.
- **Index Name:** Optional index name.
- **Text Key:** Default text extraction key.
- **Embedding:** Model used.
- **Attributes:** Optional additional attributes.
- **Input Value:** The input value to search for.
- **Weaviate URL:** The URL of the Weaviate instance (default: http://localhost:8080).
- **Search By Text:** Boolean indicating whether to search by text (default: False).
- **API Key:** The API key for authentication (optional).
- **Index name:** The name of the index in Weaviate (optional).
- **Text Key:** The key used to extract text from documents (default: "text").
- **Embedding:** The embedding model used by Weaviate.
- **Attributes:** Additional attributes to consider during indexing (optional).
---