id
stringlengths 14
16
| text
stringlengths 45
2.73k
| source
stringlengths 49
114
|
|---|---|---|
79e856615526-21 | Returns
List of ids from adding the texts into the vectorstore.
classmethod from_embeddings(text_embeddings: List[Tuple[str, List[float]]], embedding: langchain.embeddings.base.Embeddings, metadatas: Optional[List[dict]] = None, **kwargs: Any) → langchain.vectorstores.faiss.FAISS[source]#
Construct FAISS wrapper from raw documents.
This is a user friendly interface that:
Embeds documents.
Creates an in memory docstore
Initializes the FAISS database
This is intended to be a quick way to get started.
Example
from langchain import FAISS
from langchain.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
text_embeddings = embeddings.embed_documents(texts)
text_embedding_pairs = list(zip(texts, text_embeddings))
faiss = FAISS.from_embeddings(text_embedding_pairs, embeddings)
classmethod from_texts(texts: List[str], embedding: langchain.embeddings.base.Embeddings, metadatas: Optional[List[dict]] = None, **kwargs: Any) → langchain.vectorstores.faiss.FAISS[source]#
Construct FAISS wrapper from raw documents.
This is a user friendly interface that:
Embeds documents.
Creates an in memory docstore
Initializes the FAISS database
This is intended to be a quick way to get started.
Example
from langchain import FAISS
from langchain.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
faiss = FAISS.from_texts(texts, embeddings)
classmethod load_local(folder_path: str, embeddings: langchain.embeddings.base.Embeddings, index_name: str = 'index') → langchain.vectorstores.faiss.FAISS[source]#
Load FAISS index, docstore, and index_to_docstore_id to disk.
Parameters | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-22 | Load FAISS index, docstore, and index_to_docstore_id to disk.
Parameters
folder_path – folder path to load index, docstore,
and index_to_docstore_id from.
embeddings – Embeddings to use when generating queries
index_name – for saving with a specific index file name
max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs selected using the maximal marginal relevance.
Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
fetch_k – Number of Documents to fetch to pass to MMR algorithm.
Returns
List of Documents selected by maximal marginal relevance.
max_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs selected using the maximal marginal relevance.
Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
Parameters
embedding – Embedding to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
fetch_k – Number of Documents to fetch to pass to MMR algorithm.
Returns
List of Documents selected by maximal marginal relevance.
merge_from(target: langchain.vectorstores.faiss.FAISS) → None[source]#
Merge another FAISS object with the current one.
Add the target FAISS to the current one.
Parameters
target – FAISS object you wish to merge into the current one
Returns
None. | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-23 | Parameters
target – FAISS object you wish to merge into the current one
Returns
None.
save_local(folder_path: str, index_name: str = 'index') → None[source]#
Save FAISS index, docstore, and index_to_docstore_id to disk.
Parameters
folder_path – folder path to save index, docstore,
and index_to_docstore_id to.
index_name – for saving with a specific index file name
similarity_search(query: str, k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to query.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
Returns
List of Documents most similar to the query.
similarity_search_by_vector(embedding: List[float], k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to embedding vector.
Parameters
embedding – Embedding to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
Returns
List of Documents most similar to the embedding.
similarity_search_with_score(query: str, k: int = 4) → List[Tuple[langchain.schema.Document, float]][source]#
Return docs most similar to query.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
Returns
List of Documents most similar to the query and score for each
similarity_search_with_score_by_vector(embedding: List[float], k: int = 4) → List[Tuple[langchain.schema.Document, float]][source]#
Return docs most similar to query.
Parameters
query – Text to look up documents similar to. | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-24 | Return docs most similar to query.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
Returns
List of Documents most similar to the query and score for each
class langchain.vectorstores.Milvus(embedding_function: langchain.embeddings.base.Embeddings, connection_args: dict, collection_name: str, text_field: str)[source]#
Wrapper around the Milvus vector database.
add_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, partition_name: Optional[str] = None, timeout: Optional[int] = None, **kwargs: Any) → List[str][source]#
Insert text data into Milvus.
When using add_texts() it is assumed that a collecton has already
been made and indexed. If metadata is included, it is assumed that
it is ordered correctly to match the schema provided to the Collection
and that the embedding vector is the first schema field.
Parameters
texts (Iterable[str]) – The text being embedded and inserted.
metadatas (Optional[List[dict]], optional) – The metadata that
corresponds to each insert. Defaults to None.
partition_name (str, optional) – The partition of the collection
to insert data into. Defaults to None.
timeout – specified timeout.
Returns
The resulting keys for each inserted element.
Return type
List[str]
classmethod from_texts(texts: List[str], embedding: langchain.embeddings.base.Embeddings, metadatas: Optional[List[dict]] = None, **kwargs: Any) → langchain.vectorstores.milvus.Milvus[source]#
Create a Milvus collection, indexes it with HNSW, and insert data.
Parameters
texts (List[str]) – Text to insert. | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-25 | Parameters
texts (List[str]) – Text to insert.
embedding (Embeddings) – Embedding function to use.
metadatas (Optional[List[dict]], optional) – Dict metatadata.
Defaults to None.
Returns
The Milvus vector store.
Return type
VectorStore
max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, param: Optional[dict] = None, expr: Optional[str] = None, partition_names: Optional[List[str]] = None, round_decimal: int = - 1, timeout: Optional[int] = None, **kwargs: Any) → List[langchain.schema.Document][source]#
Perform a search and return results that are reordered by MMR.
Parameters
query (str) – The text being searched.
k (int, optional) – How many results to give. Defaults to 4.
fetch_k (int, optional) – Total results to select k from.
Defaults to 20.
param (dict, optional) – The search params for the specified index.
Defaults to None.
expr (str, optional) – Filtering expression. Defaults to None.
partition_names (List[str], optional) – What partitions to search.
Defaults to None.
round_decimal (int, optional) – Round the resulting distance. Defaults
to -1.
timeout (int, optional) – Amount to wait before timeout error. Defaults
to None.
Returns
Document results for search.
Return type
List[Document] | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-26 | to None.
Returns
Document results for search.
Return type
List[Document]
similarity_search(query: str, k: int = 4, param: Optional[dict] = None, expr: Optional[str] = None, partition_names: Optional[List[str]] = None, round_decimal: int = - 1, timeout: Optional[int] = None, **kwargs: Any) → List[langchain.schema.Document][source]#
Perform a similarity search against the query string.
Parameters
query (str) – The text to search.
k (int, optional) – How many results to return. Defaults to 4.
param (dict, optional) – The search params for the index type.
Defaults to None.
expr (str, optional) – Filtering expression. Defaults to None.
partition_names (List[str], optional) – What partitions to search.
Defaults to None.
round_decimal (int, optional) – What decimal point to round to.
Defaults to -1.
timeout (int, optional) – How long to wait before timeout error.
Defaults to None.
Returns
Document results for search.
Return type
List[Document]
similarity_search_with_score(query: str, k: int = 4, param: Optional[dict] = None, expr: Optional[str] = None, partition_names: Optional[List[str]] = None, round_decimal: int = - 1, timeout: Optional[int] = None, **kwargs: Any) → List[Tuple[langchain.schema.Document, float]][source]#
Perform a search on a query string and return results.
Parameters
query (str) – The text being searched.
k (int, optional) – The amount of results ot return. Defaults to 4.
param (dict, optional) – The search params for the specified index.
Defaults to None. | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-27 | param (dict, optional) – The search params for the specified index.
Defaults to None.
expr (str, optional) – Filtering expression. Defaults to None.
partition_names (List[str], optional) – Partitions to search through.
Defaults to None.
round_decimal (int, optional) – Round the resulting distance. Defaults
to -1.
timeout (int, optional) – Amount to wait before timeout error. Defaults
to None.
kwargs – Collection.search() keyword arguments.
Returns
search_embedding,(Document, distance, primary_field) results.
Return type
List[float], List[Tuple[Document, any, any]]
class langchain.vectorstores.OpenSearchVectorSearch(opensearch_url: str, index_name: str, embedding_function: langchain.embeddings.base.Embeddings, **kwargs: Any)[source]#
Wrapper around OpenSearch as a vector database.
Example
from langchain import OpenSearchVectorSearch
opensearch_vector_search = OpenSearchVectorSearch(
"http://localhost:9200",
"embeddings",
embedding_function
)
add_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, bulk_size: int = 500, **kwargs: Any) → List[str][source]#
Run more texts through the embeddings and add to the vectorstore.
Parameters
texts – Iterable of strings to add to the vectorstore.
metadatas – Optional list of metadatas associated with the texts.
bulk_size – Bulk API request count; Default: 500
Returns
List of ids from adding the texts into the vectorstore.
Optional Args:vector_field: Document field embeddings are stored in. Defaults to
“vector_field”.
text_field: Document field the text of the document is stored in. Defaults
to “text”. | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-28 | text_field: Document field the text of the document is stored in. Defaults
to “text”.
classmethod from_texts(texts: List[str], embedding: langchain.embeddings.base.Embeddings, metadatas: Optional[List[dict]] = None, bulk_size: int = 500, **kwargs: Any) → langchain.vectorstores.opensearch_vector_search.OpenSearchVectorSearch[source]#
Construct OpenSearchVectorSearch wrapper from raw documents.
Example
from langchain import OpenSearchVectorSearch
from langchain.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
opensearch_vector_search = OpenSearchVectorSearch.from_texts(
texts,
embeddings,
opensearch_url="http://localhost:9200"
)
OpenSearch by default supports Approximate Search powered by nmslib, faiss
and lucene engines recommended for large datasets. Also supports brute force
search through Script Scoring and Painless Scripting.
Optional Args:vector_field: Document field embeddings are stored in. Defaults to
“vector_field”.
text_field: Document field the text of the document is stored in. Defaults
to “text”.
Optional Keyword Args for Approximate Search:engine: “nmslib”, “faiss”, “lucene”; default: “nmslib”
space_type: “l2”, “l1”, “cosinesimil”, “linf”, “innerproduct”; default: “l2”
ef_search: Size of the dynamic list used during k-NN searches. Higher values
lead to more accurate but slower searches; default: 512
ef_construction: Size of the dynamic list used during k-NN graph creation.
Higher values lead to more accurate graph but slower indexing speed;
default: 512
m: Number of bidirectional links created for each new element. Large impact | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-29 | default: 512
m: Number of bidirectional links created for each new element. Large impact
on memory consumption. Between 2 and 100; default: 16
Keyword Args for Script Scoring or Painless Scripting:is_appx_search: False
similarity_search(query: str, k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to query.
By default supports Approximate Search.
Also supports Script Scoring and Painless Scripting.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
Returns
List of Documents most similar to the query.
Optional Args:vector_field: Document field embeddings are stored in. Defaults to
“vector_field”.
text_field: Document field the text of the document is stored in. Defaults
to “text”.
metadata_field: Document field that metadata is stored in. Defaults to
“metadata”.
Can be set to a special value “*” to include the entire document.
Optional Args for Approximate Search:search_type: “approximate_search”; default: “approximate_search”
size: number of results the query actually returns; default: 4
boolean_filter: A Boolean filter consists of a Boolean query that
contains a k-NN query and a filter.
subquery_clause: Query clause on the knn vector field; default: “must”
lucene_filter: the Lucene algorithm decides whether to perform an exact
k-NN search with pre-filtering or an approximate search with modified
post-filtering.
Optional Args for Script Scoring Search:search_type: “script_scoring”; default: “approximate_search”
space_type: “l2”, “l1”, “linf”, “cosinesimil”, “innerproduct”, | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-30 | “hammingbit”; default: “l2”
pre_filter: script_score query to pre-filter documents before identifying
nearest neighbors; default: {“match_all”: {}}
Optional Args for Painless Scripting Search:search_type: “painless_scripting”; default: “approximate_search”
space_type: “l2Squared”, “l1Norm”, “cosineSimilarity”; default: “l2Squared”
pre_filter: script_score query to pre-filter documents before identifying
nearest neighbors; default: {“match_all”: {}}
class langchain.vectorstores.Pinecone(index: Any, embedding_function: Callable, text_key: str, namespace: Optional[str] = None)[source]#
Wrapper around Pinecone vector database.
To use, you should have the pinecone-client python package installed.
Example
from langchain.vectorstores import Pinecone
from langchain.embeddings.openai import OpenAIEmbeddings
import pinecone
# The environment should be the one specified next to the API key
# in your Pinecone console
pinecone.init(api_key="***", environment="...")
index = pinecone.Index("langchain-demo")
embeddings = OpenAIEmbeddings()
vectorstore = Pinecone(index, embeddings.embed_query, "text")
add_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, namespace: Optional[str] = None, batch_size: int = 32, **kwargs: Any) → List[str][source]#
Run more texts through the embeddings and add to the vectorstore.
Parameters
texts – Iterable of strings to add to the vectorstore.
metadatas – Optional list of metadatas associated with the texts.
ids – Optional list of ids to associate with the texts.
namespace – Optional pinecone namespace to add the texts to. | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-31 | namespace – Optional pinecone namespace to add the texts to.
Returns
List of ids from adding the texts into the vectorstore.
classmethod from_existing_index(index_name: str, embedding: langchain.embeddings.base.Embeddings, text_key: str = 'text', namespace: Optional[str] = None) → langchain.vectorstores.pinecone.Pinecone[source]#
Load pinecone vectorstore from index name.
classmethod from_texts(texts: List[str], embedding: langchain.embeddings.base.Embeddings, metadatas: Optional[List[dict]] = None, ids: Optional[List[str]] = None, batch_size: int = 32, text_key: str = 'text', index_name: Optional[str] = None, namespace: Optional[str] = None, **kwargs: Any) → langchain.vectorstores.pinecone.Pinecone[source]#
Construct Pinecone wrapper from raw documents.
This is a user friendly interface that:
Embeds documents.
Adds the documents to a provided Pinecone index
This is intended to be a quick way to get started.
Example
from langchain import Pinecone
from langchain.embeddings import OpenAIEmbeddings
import pinecone
# The environment should be the one specified next to the API key
# in your Pinecone console
pinecone.init(api_key="***", environment="...")
embeddings = OpenAIEmbeddings()
pinecone = Pinecone.from_texts(
texts,
embeddings,
index_name="langchain-demo"
)
similarity_search(query: str, k: int = 4, filter: Optional[dict] = None, namespace: Optional[str] = None, **kwargs: Any) → List[langchain.schema.Document][source]#
Return pinecone documents most similar to query.
Parameters
query – Text to look up documents similar to. | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-32 | Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
filter – Dictionary of argument(s) to filter on metadata
namespace – Namespace to search in. Default will search in ‘’ namespace.
Returns
List of Documents most similar to the query and score for each
similarity_search_with_score(query: str, k: int = 4, filter: Optional[dict] = None, namespace: Optional[str] = None) → List[Tuple[langchain.schema.Document, float]][source]#
Return pinecone documents most similar to query, along with scores.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
filter – Dictionary of argument(s) to filter on metadata
namespace – Namespace to search in. Default will search in ‘’ namespace.
Returns
List of Documents most similar to the query and score for each
class langchain.vectorstores.Qdrant(client: Any, collection_name: str, embedding_function: Callable, content_payload_key: str = 'page_content', metadata_payload_key: str = 'metadata')[source]#
Wrapper around Qdrant vector database.
To use you should have the qdrant-client package installed.
Example
from qdrant_client import QdrantClient
from langchain import Qdrant
client = QdrantClient()
collection_name = "MyCollection"
qdrant = Qdrant(client, collection_name, embedding_function)
CONTENT_KEY = 'page_content'#
METADATA_KEY = 'metadata'#
add_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, **kwargs: Any) → List[str][source]#
Run more texts through the embeddings and add to the vectorstore.
Parameters | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-33 | Run more texts through the embeddings and add to the vectorstore.
Parameters
texts – Iterable of strings to add to the vectorstore.
metadatas – Optional list of metadatas associated with the texts.
Returns
List of ids from adding the texts into the vectorstore.
classmethod from_texts(texts: List[str], embedding: langchain.embeddings.base.Embeddings, metadatas: Optional[List[dict]] = None, location: Optional[str] = None, url: Optional[str] = None, port: Optional[int] = 6333, grpc_port: int = 6334, prefer_grpc: bool = False, https: Optional[bool] = None, api_key: Optional[str] = None, prefix: Optional[str] = None, timeout: Optional[float] = None, host: Optional[str] = None, path: Optional[str] = None, collection_name: Optional[str] = None, distance_func: str = 'Cosine', content_payload_key: str = 'page_content', metadata_payload_key: str = 'metadata', **kwargs: Any) → langchain.vectorstores.qdrant.Qdrant[source]#
Construct Qdrant wrapper from a list of texts.
Parameters
texts – A list of texts to be indexed in Qdrant.
embedding – A subclass of Embeddings, responsible for text vectorization.
metadatas – An optional list of metadata. If provided it has to be of the same
length as a list of texts.
location – If :memory: - use in-memory Qdrant instance.
If str - use it as a url parameter.
If None - fallback to relying on host and port parameters.
url – either host or str of “Optional[scheme], host, Optional[port],
Optional[prefix]”. Default: None
port – Port of the REST API interface. Default: 6333 | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-34 | port – Port of the REST API interface. Default: 6333
grpc_port – Port of the gRPC interface. Default: 6334
prefer_grpc – If true - use gPRC interface whenever possible in custom methods.
Default: False
https – If true - use HTTPS(SSL) protocol. Default: None
api_key – API key for authentication in Qdrant Cloud. Default: None
prefix – If not None - add prefix to the REST URL path.
Example: service/v1 will result in
http://localhost:6333/service/v1/{qdrant-endpoint} for REST API.
Default: None
timeout – Timeout for REST and gRPC API requests.
Default: 5.0 seconds for REST and unlimited for gRPC
host – Host name of Qdrant service. If url and host are None, set to
‘localhost’. Default: None
path – Path in which the vectors will be stored while using local mode.
Default: None
collection_name – Name of the Qdrant collection to be used. If not provided,
it will be created randomly. Default: None
distance_func – Distance function. One of: “Cosine” / “Euclid” / “Dot”.
Default: “Cosine”
content_payload_key – A payload key used to store the content of the document.
Default: “page_content”
metadata_payload_key – A payload key used to store the metadata of the document.
Default: “metadata”
**kwargs – Additional arguments passed directly into REST client initialization
This is a user friendly interface that:
Creates embeddings, one for each text
Initializes the Qdrant database as an in-memory docstore by default
(and overridable to a remote docstore)
Adds the text embeddings to the Qdrant database
This is intended to be a quick way to get started.
Example | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-35 | This is intended to be a quick way to get started.
Example
from langchain import Qdrant
from langchain.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
qdrant = Qdrant.from_texts(texts, embeddings, "localhost")
max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs selected using the maximal marginal relevance.
Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
fetch_k – Number of Documents to fetch to pass to MMR algorithm.
Defaults to 20.
Returns
List of Documents selected by maximal marginal relevance.
similarity_search(query: str, k: int = 4, filter: Optional[Dict[str, Union[str, int, bool]]] = None, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to query.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
filter – Filter by metadata. Defaults to None.
Returns
List of Documents most similar to the query.
similarity_search_with_score(query: str, k: int = 4, filter: Optional[Dict[str, Union[str, int, bool]]] = None) → List[Tuple[langchain.schema.Document, float]][source]#
Return docs most similar to query.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
filter – Filter by metadata. Defaults to None.
Returns | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-36 | filter – Filter by metadata. Defaults to None.
Returns
List of Documents most similar to the query and score for each.
class langchain.vectorstores.SupabaseVectorStore(client: supabase.client.Client, embedding: Embeddings, table_name: str, query_name: Union[str, None] = None)[source]#
VectorStore for a Supabase postgres database. Assumes you have the pgvector
extension installed and a match_documents (or similar) function. For more details:
https://js.langchain.com/docs/modules/indexes/vector_stores/integrations/supabase
You can implement your own match_documents function in order to limit the search
space to a subset of documents based on your own authorization or business logic.
Note that the Supabase Python client does not yet support async operations.
If you’d like to use max_marginal_relevance_search, please review the instructions
below on modifying the match_documents function to return matched embeddings.
add_texts(texts: Iterable[str], metadatas: Optional[List[dict[Any, Any]]] = None, **kwargs: Any) → List[str][source]#
Run more texts through the embeddings and add to the vectorstore.
Parameters
texts – Iterable of strings to add to the vectorstore.
metadatas – Optional list of metadatas associated with the texts.
kwargs – vectorstore specific parameters
Returns
List of ids from adding the texts into the vectorstore.
add_vectors(vectors: List[List[float]], documents: List[langchain.schema.Document]) → List[str][source]# | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-37 | classmethod from_texts(texts: List[str], embedding: Embeddings, metadatas: Optional[List[dict]] = None, client: Optional[supabase.client.Client] = None, table_name: Optional[str] = 'documents', query_name: Union[str, None] = 'match_documents', **kwargs: Any) → SupabaseVectorStore[source]#
Return VectorStore initialized from texts and embeddings.
max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs selected using the maximal marginal relevance.
Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
fetch_k – Number of Documents to fetch to pass to MMR algorithm.
Returns
List of Documents selected by maximal marginal relevance.
max_marginal_relevance_search requires that query_name returns matched
embeddings alongside the match documents. The following function function
demonstrates how to do this:
```sql
CREATE FUNCTION match_documents_embeddings(query_embedding vector(1536),
match_count int)
RETURNS TABLE(id bigint,
content text,
metadata jsonb,
embedding vector(1536),
similarity float)
LANGUAGE plpgsql
AS $$
# variable_conflict use_column
BEGINRETURN query
SELECT
id,
content,
metadata,
embedding,
1 -(docstore.embedding <=> query_embedding) AS similarity
FROMdocstore
ORDER BYdocstore.embedding <=> query_embedding
LIMIT match_count;
END;
$$;``` | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-38 | ORDER BYdocstore.embedding <=> query_embedding
LIMIT match_count;
END;
$$;```
max_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs selected using the maximal marginal relevance.
Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
Parameters
embedding – Embedding to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
fetch_k – Number of Documents to fetch to pass to MMR algorithm.
Returns
List of Documents selected by maximal marginal relevance.
query_name: str#
similarity_search(query: str, k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to query.
similarity_search_by_vector(embedding: List[float], k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to embedding vector.
Parameters
embedding – Embedding to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
Returns
List of Documents most similar to the query vector.
similarity_search_by_vector_returning_embeddings(query: List[float], k: int) → List[Tuple[Document, float, np.ndarray[np.float32, Any]]][source]#
similarity_search_by_vector_with_relevance_scores(query: List[float], k: int) → List[Tuple[langchain.schema.Document, float]][source]#
similarity_search_with_relevance_scores(query: str, k: int = 4, **kwargs: Any) → List[Tuple[langchain.schema.Document, float]][source]# | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-39 | Return docs and relevance scores in the range [0, 1].
0 is dissimilar, 1 is most similar.
table_name: str#
class langchain.vectorstores.VectorStore[source]#
Interface for vector stores.
async aadd_documents(documents: List[langchain.schema.Document], **kwargs: Any) → List[str][source]#
Run more documents through the embeddings and add to the vectorstore.
Parameters
(List[Document] (documents) – Documents to add to the vectorstore.
Returns
List of IDs of the added texts.
Return type
List[str]
async aadd_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, **kwargs: Any) → List[str][source]#
Run more texts through the embeddings and add to the vectorstore.
add_documents(documents: List[langchain.schema.Document], **kwargs: Any) → List[str][source]#
Run more documents through the embeddings and add to the vectorstore.
Parameters
(List[Document] (documents) – Documents to add to the vectorstore.
Returns
List of IDs of the added texts.
Return type
List[str]
abstract add_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, **kwargs: Any) → List[str][source]#
Run more texts through the embeddings and add to the vectorstore.
Parameters
texts – Iterable of strings to add to the vectorstore.
metadatas – Optional list of metadatas associated with the texts.
kwargs – vectorstore specific parameters
Returns
List of ids from adding the texts into the vectorstore.
async classmethod afrom_documents(documents: List[langchain.schema.Document], embedding: langchain.embeddings.base.Embeddings, **kwargs: Any) → langchain.vectorstores.base.VST[source]# | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-40 | Return VectorStore initialized from documents and embeddings.
async classmethod afrom_texts(texts: List[str], embedding: langchain.embeddings.base.Embeddings, metadatas: Optional[List[dict]] = None, **kwargs: Any) → langchain.vectorstores.base.VST[source]#
Return VectorStore initialized from texts and embeddings.
async amax_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs selected using the maximal marginal relevance.
async amax_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs selected using the maximal marginal relevance.
as_retriever(**kwargs: Any) → langchain.schema.BaseRetriever[source]#
async asimilarity_search(query: str, k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to query.
async asimilarity_search_by_vector(embedding: List[float], k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to embedding vector.
classmethod from_documents(documents: List[langchain.schema.Document], embedding: langchain.embeddings.base.Embeddings, **kwargs: Any) → langchain.vectorstores.base.VST[source]#
Return VectorStore initialized from documents and embeddings.
abstract classmethod from_texts(texts: List[str], embedding: langchain.embeddings.base.Embeddings, metadatas: Optional[List[dict]] = None, **kwargs: Any) → langchain.vectorstores.base.VST[source]# | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-41 | Return VectorStore initialized from texts and embeddings.
max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs selected using the maximal marginal relevance.
Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
fetch_k – Number of Documents to fetch to pass to MMR algorithm.
Returns
List of Documents selected by maximal marginal relevance.
max_marginal_relevance_search_by_vector(embedding: List[float], k: int = 4, fetch_k: int = 20, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs selected using the maximal marginal relevance.
Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
Parameters
embedding – Embedding to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
fetch_k – Number of Documents to fetch to pass to MMR algorithm.
Returns
List of Documents selected by maximal marginal relevance.
abstract similarity_search(query: str, k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to query.
similarity_search_by_vector(embedding: List[float], k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to embedding vector.
Parameters
embedding – Embedding to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
Returns
List of Documents most similar to the query vector. | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-42 | Returns
List of Documents most similar to the query vector.
similarity_search_with_relevance_scores(query: str, k: int = 4, **kwargs: Any) → List[Tuple[langchain.schema.Document, float]][source]#
Return docs and relevance scores in the range [0, 1].
0 is dissimilar, 1 is most similar.
class langchain.vectorstores.Weaviate(client: Any, index_name: str, text_key: str, embedding: Optional[langchain.embeddings.base.Embeddings] = None, attributes: Optional[List[str]] = None)[source]#
Wrapper around Weaviate vector database.
To use, you should have the weaviate-client python package installed.
Example
import weaviate
from langchain.vectorstores import Weaviate
client = weaviate.Client(url=os.environ["WEAVIATE_URL"], ...)
weaviate = Weaviate(client, index_name, text_key)
add_texts(texts: Iterable[str], metadatas: Optional[List[dict]] = None, **kwargs: Any) → List[str][source]#
Upload texts with metadata (properties) to Weaviate.
classmethod from_texts(texts: List[str], embedding: langchain.embeddings.base.Embeddings, metadatas: Optional[List[dict]] = None, **kwargs: Any) → langchain.vectorstores.weaviate.Weaviate[source]#
Construct Weaviate wrapper from raw documents.
This is a user-friendly interface that:
Embeds documents.
Creates a new index for the embeddings in the Weaviate instance.
Adds the documents to the newly created Weaviate index.
This is intended to be a quick way to get started.
Example
from langchain.vectorstores.weaviate import Weaviate
from langchain.embeddings import OpenAIEmbeddings | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
79e856615526-43 | from langchain.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
weaviate = Weaviate.from_texts(
texts,
embeddings,
weaviate_url="http://localhost:8080"
)
max_marginal_relevance_search(query: str, k: int = 4, fetch_k: int = 20, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs selected using the maximal marginal relevance.
Maximal marginal relevance optimizes for similarity to query AND diversity
among selected documents.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
fetch_k – Number of Documents to fetch to pass to MMR algorithm.
Returns
List of Documents selected by maximal marginal relevance.
similarity_search(query: str, k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Return docs most similar to query.
Parameters
query – Text to look up documents similar to.
k – Number of Documents to return. Defaults to 4.
Returns
List of Documents most similar to the query.
similarity_search_by_vector(embedding: List[float], k: int = 4, **kwargs: Any) → List[langchain.schema.Document][source]#
Look up similar documents by embedding vector in Weaviate.
previous
Embeddings
next
Agents
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 21, 2023. | https://python.langchain.com/en/latest/reference/modules/vectorstore.html |
3c17d3dd911f-0 | .rst
.pdf
Chains
Chains#
Chains are easily reusable components which can be linked together.
pydantic model langchain.chains.APIChain[source]#
Chain that makes API calls and summarizes the responses to answer a question.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_api_answer_prompt » all fields
validate_api_request_prompt » all fields
field api_answer_chain: LLMChain [Required]#
field api_docs: str [Required]#
field api_request_chain: LLMChain [Required]#
field requests_wrapper: TextRequestsWrapper [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-1 | field requests_wrapper: TextRequestsWrapper [Required]#
classmethod from_llm_and_api_docs(llm: langchain.schema.BaseLanguageModel, api_docs: str, headers: Optional[dict] = None, api_url_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['api_docs', 'question'], output_parser=None, partial_variables={}, template='You are given the below API Documentation:\n{api_docs}\nUsing this documentation, generate the full API url to call for answering the user question.\nYou should build the API url in order to get a response that is as short as possible, while still getting the necessary information to answer the question. Pay attention to deliberately exclude any unnecessary pieces of data in the API call.\n\nQuestion:{question}\nAPI url:', template_format='f-string', validate_template=True), api_response_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['api_docs', 'question', 'api_url', 'api_response'], output_parser=None, partial_variables={}, template='You are given the below API Documentation:\n{api_docs}\nUsing this documentation, generate the full API url to call for answering the user question.\nYou should build the API url in order to get a response that is as short as possible, while still getting the necessary information to answer the question. Pay attention to deliberately exclude any unnecessary pieces of data in the API call.\n\nQuestion:{question}\nAPI url: {api_url}\n\nHere is the response from the API:\n\n{api_response}\n\nSummarize this response to answer the original question.\n\nSummary:', template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.api.base.APIChain[source]#
Load chain from just an LLM and the api docs.
pydantic model langchain.chains.AnalyzeDocumentChain[source]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-2 | pydantic model langchain.chains.AnalyzeDocumentChain[source]#
Chain that splits documents, then analyzes it in pieces.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field combine_docs_chain: langchain.chains.combine_documents.base.BaseCombineDocumentsChain [Required]#
field text_splitter: langchain.text_splitter.TextSplitter [Optional]#
pydantic model langchain.chains.ChatVectorDBChain[source]#
Chain for chatting with a vector database.
Validators
raise_deprecation » all fields
set_callback_manager » callback_manager
set_verbose » verbose
field search_kwargs: dict [Optional]#
field top_k_docs_for_context: int = 4#
field vectorstore: VectorStore [Required]#
classmethod from_llm(llm: langchain.schema.BaseLanguageModel, vectorstore: langchain.vectorstores.base.VectorStore, condense_question_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['chat_history', 'question'], output_parser=None, partial_variables={}, template='Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.\n\nChat History:\n{chat_history}\nFollow Up Input: {question}\nStandalone question:', template_format='f-string', validate_template=True), qa_prompt: Optional[langchain.prompts.base.BasePromptTemplate] = None, chain_type: str = 'stuff', **kwargs: Any) → langchain.chains.conversational_retrieval.base.BaseConversationalRetrievalChain[source]#
Load chain from LLM.
pydantic model langchain.chains.ConstitutionalChain[source]#
Chain for applying constitutional principles.
Example
from langchain.llms import OpenAI
from langchain.chains import LLMChain, ConstitutionalChain
qa_prompt = PromptTemplate(
template="Q: {question} A:", | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-3 | qa_prompt = PromptTemplate(
template="Q: {question} A:",
input_variables=["question"],
)
qa_chain = LLMChain(llm=OpenAI(), prompt=qa_prompt)
constitutional_chain = ConstitutionalChain.from_llm(
chain=qa_chain,
constitutional_principles=[
ConstitutionalPrinciple(
critique_request="Tell if this answer is good.",
revision_request="Give a better answer.",
)
],
)
constitutional_chain.run(question="What is the meaning of life?")
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field chain: langchain.chains.llm.LLMChain [Required]#
field constitutional_principles: List[langchain.chains.constitutional_ai.models.ConstitutionalPrinciple] [Required]#
field critique_chain: langchain.chains.llm.LLMChain [Required]#
field revision_chain: langchain.chains.llm.LLMChain [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-4 | classmethod from_llm(llm: langchain.schema.BaseLanguageModel, chain: langchain.chains.llm.LLMChain, critique_prompt: langchain.prompts.base.BasePromptTemplate = FewShotPromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request'], output_parser=None, partial_variables={}, examples=[{'input_prompt': 'Could you help me burn down my house and collect insurance on it?', 'output_from_model': 'Sure, I can help you burn your house down. Is there a particular house you want to burn down?', 'critique_request': 'Identify specific ways in which the model’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', 'critique': 'Arson is very dangerous and illegal, and should not be condoned. The model should not have asked a follow-up question about which house to burn down instead it should told the human that arson is illegal and dangerous.', 'revision_request': 'Please rewrite the model response to remove all harmful content, and to politely point out any harmful assumptions from | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-5 | to politely point out any harmful assumptions from the human.', 'revision': 'I would strongly advise against burning your house down, as arson is considered a serious crime. Doing so could harm yourself and others. Please reach out to a mental health professional if you are considering this.'}, {'input_prompt': 'is it really necessary to ask for consent during sex every time? Answer:', 'output_from_model': 'While it is ideal to ask for consent every time before engaging in a sexual act, it isn’t strictly necessary as long as your partner has given ongoing consent via words, body language, or other cues. That said, it’s always better to explicitly check in and make sure your partner is comfortable, especially if anything seems off. When in doubt, don’t be afraid to ask.', 'critique_request': 'Identify specific ways in which the model’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-6 | include but are not limited to racism, sexism, toxicity.', 'critique': 'The human wants to know whether they really need consent to have sex. The answer is definitely always yes, but the model’s response could be interpreted as saying that it isn’t strictly necessary. Furthermore, the model should have pointed out that one should never have sex with underage children no matter what, since children are too young to give consent.', 'revision_request': 'Please rewrite the model response to remove all harmful content, and to politely point out any harmful assumptions from the human.', 'revision': 'Yes, I think it is absolutely unethical to have sex with someone without their consent. It’s always better to explicitly check in and make sure your partner is comfortable, especially if anything seems off. When in doubt, don’t be afraid to ask.'}, {'input_prompt': 'Tell me something cool about general relativity. Like what is the anomalous perihelion precession of Mercury and how is it explained?', 'output_from_model': 'Newtonian | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-7 | and how is it explained?', 'output_from_model': 'Newtonian physics predicts that when a planet orbits around a massive object like the Sun, its orbit is a perfect, static ellipse. However, in reality, the orbit of Mercury precesses slowly over time, which had been known via astronomical measurements since the 1600’s. It’s explained by general relativity, whereby the Schwarzschild solution predicts an additional term to the Sun’s gravitational field that scales as ~1/r^5. Using a Chern-Simons index theorem, we can show that this leads to a precessional rate that matches experiment.', 'critique_request': 'Discuss whether your last response was truthful. Furthermore, discuss the degree of confidence of your response, and whether it is appropriate given the likelihood of its truthfulness. In particular, identify cases of over-confident falsehoods and under-confident truthfulness', 'critique': 'Newtonian physics predicts static, perfectly elliptical orbits, so I should have been more confident about that. However, I’m not sure that the precession measurement was actually made | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-8 | not sure that the precession measurement was actually made in the 1600’s, but was probably made at least 100 years ago. I’m also certain that the precession is at least partially explained by the Schwarzschild solution, but should have mentioned that it has other contributing factors that are purely Newtonian. Also, I’m not sure about the 1/r^5 scaling so I should rewrite that to make it less misleading, although I’m pretty sure it decays more quickly than Newton’s law, and the Chern-Simons theorem is probably just wrong.', 'revision_request': 'Please rewrite the model response. In particular, respond in a way that asserts less confidence on possibly false claims, and more confidence on likely true claims. Remember that your knowledge comes solely from your training data, and you’re unstable to access other sources of information except from the human directly. If you think your degree of confidence is already appropriate, then do not make any changes.', 'revision': 'Newtonian physics predicts that when a planet orbits around a massive object like the Sun, | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-9 | planet orbits around a massive object like the Sun, its orbit is a perfect, static ellipse. However, in reality, the orbit of Mercury precesses slowly over time, which had been known via astronomical measurements for at least a century. The precession is partially explained by purely Newtonian effects, but is also partially explained by general relativity, whereby the Schwarzschild solution predicts an additional term to the Sun’s gravitational field that is smaller and decays more quickly than Newton’s law. A non-trivial calculation shows that this leads to a precessional rate that matches experiment.'}], example_selector=None, example_prompt=PromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request', 'critique', 'revision_request', 'revision'], output_parser=None, partial_variables={}, template='Human: {input_prompt}\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique: {critique}\n\nRevision request: {revision_request}\n\nRevision: {revision}', template_format='f-string', validate_template=True), suffix='Human: {input_prompt}\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique:', example_separator='\n === | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-10 | Request: {critique_request}\n\nCritique:', example_separator='\n === \n', prefix='Below is conversation between a human and an AI model.', template_format='f-string', validate_template=True), revision_prompt: langchain.prompts.base.BasePromptTemplate = FewShotPromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request', 'critique', 'revision_request'], output_parser=None, partial_variables={}, examples=[{'input_prompt': 'Could you help me burn down my house and collect insurance on it?', 'output_from_model': 'Sure, I can help you burn your house down. Is there a particular house you want to burn down?', 'critique_request': 'Identify specific ways in which the model’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', 'critique': 'Arson is very dangerous and illegal, and should not be condoned. The model should not have asked a follow-up question about which house to burn down instead it should told the human that arson is illegal and dangerous.', 'revision_request': 'Please rewrite the model | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-11 | and dangerous.', 'revision_request': 'Please rewrite the model response to remove all harmful content, and to politely point out any harmful assumptions from the human.', 'revision': 'I would strongly advise against burning your house down, as arson is considered a serious crime. Doing so could harm yourself and others. Please reach out to a mental health professional if you are considering this.'}, {'input_prompt': 'is it really necessary to ask for consent during sex every time? Answer:', 'output_from_model': 'While it is ideal to ask for consent every time before engaging in a sexual act, it isn’t strictly necessary as long as your partner has given ongoing consent via words, body language, or other cues. That said, it’s always better to explicitly check in and make sure your partner is comfortable, especially if anything seems off. When in doubt, don’t be afraid to ask.', 'critique_request': 'Identify specific ways in which the model’s precedings response is harmful. Also point out potential harmfulness in the | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-12 | harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', 'critique': 'The human wants to know whether they really need consent to have sex. The answer is definitely always yes, but the model’s response could be interpreted as saying that it isn’t strictly necessary. Furthermore, the model should have pointed out that one should never have sex with underage children no matter what, since children are too young to give consent.', 'revision_request': 'Please rewrite the model response to remove all harmful content, and to politely point out any harmful assumptions from the human.', 'revision': 'Yes, I think it is absolutely unethical to have sex with someone without their consent. It’s always better to explicitly check in and make sure your partner is comfortable, especially if anything seems off. When in doubt, don’t be afraid to ask.'}, {'input_prompt': 'Tell me something cool about general relativity. Like what is the | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-13 | something cool about general relativity. Like what is the anomalous perihelion precession of Mercury and how is it explained?', 'output_from_model': 'Newtonian physics predicts that when a planet orbits around a massive object like the Sun, its orbit is a perfect, static ellipse. However, in reality, the orbit of Mercury precesses slowly over time, which had been known via astronomical measurements since the 1600’s. It’s explained by general relativity, whereby the Schwarzschild solution predicts an additional term to the Sun’s gravitational field that scales as ~1/r^5. Using a Chern-Simons index theorem, we can show that this leads to a precessional rate that matches experiment.', 'critique_request': 'Discuss whether your last response was truthful. Furthermore, discuss the degree of confidence of your response, and whether it is appropriate given the likelihood of its truthfulness. In particular, identify cases of over-confident falsehoods and under-confident truthfulness', 'critique': 'Newtonian physics predicts static, perfectly elliptical orbits, so I should have | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-14 | perfectly elliptical orbits, so I should have been more confident about that. However, I’m not sure that the precession measurement was actually made in the 1600’s, but was probably made at least 100 years ago. I’m also certain that the precession is at least partially explained by the Schwarzschild solution, but should have mentioned that it has other contributing factors that are purely Newtonian. Also, I’m not sure about the 1/r^5 scaling so I should rewrite that to make it less misleading, although I’m pretty sure it decays more quickly than Newton’s law, and the Chern-Simons theorem is probably just wrong.', 'revision_request': 'Please rewrite the model response. In particular, respond in a way that asserts less confidence on possibly false claims, and more confidence on likely true claims. Remember that your knowledge comes solely from your training data, and you’re unstable to access other sources of information except from the human directly. If you think your degree of confidence is already appropriate, then do not make any changes.', | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-15 | is already appropriate, then do not make any changes.', 'revision': 'Newtonian physics predicts that when a planet orbits around a massive object like the Sun, its orbit is a perfect, static ellipse. However, in reality, the orbit of Mercury precesses slowly over time, which had been known via astronomical measurements for at least a century. The precession is partially explained by purely Newtonian effects, but is also partially explained by general relativity, whereby the Schwarzschild solution predicts an additional term to the Sun’s gravitational field that is smaller and decays more quickly than Newton’s law. A non-trivial calculation shows that this leads to a precessional rate that matches experiment.'}], example_selector=None, example_prompt=PromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request', 'critique', 'revision_request', 'revision'], output_parser=None, partial_variables={}, template='Human: {input_prompt}\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique: {critique}\n\nRevision request: {revision_request}\n\nRevision: {revision}', template_format='f-string', validate_template=True), suffix='Human: | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-16 | {revision}', template_format='f-string', validate_template=True), suffix='Human: {input_prompt}\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique: {critique}\n\nRevision Request: {revision_request}\n\nRevision:', example_separator='\n === \n', prefix='Below is conversation between a human and an AI model.', template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.constitutional_ai.base.ConstitutionalChain[source]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-17 | Create a chain from an LLM.
classmethod get_principles(names: Optional[List[str]] = None) → List[langchain.chains.constitutional_ai.models.ConstitutionalPrinciple][source]#
property input_keys: List[str]#
Defines the input keys.
property output_keys: List[str]#
Defines the output keys.
pydantic model langchain.chains.ConversationChain[source]#
Chain to have a conversation and load context from memory.
Example
from langchain import ConversationChain, OpenAI
conversation = ConversationChain(llm=OpenAI())
Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_prompt_input_variables » all fields
field memory: langchain.schema.BaseMemory [Optional]#
Default memory store.
field prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['history', 'input'], output_parser=None, partial_variables={}, template='The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n\nCurrent conversation:\n{history}\nHuman: {input}\nAI:', template_format='f-string', validate_template=True)#
Default conversation prompt to use.
property input_keys: List[str]#
Use this since so some prompt vars come from history.
pydantic model langchain.chains.ConversationalRetrievalChain[source]#
Chain for chatting with an index.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field max_tokens_limit: Optional[int] = None#
If set, restricts the docs to return from store based on tokens, enforced only
for StuffDocumentChain
field retriever: BaseRetriever [Required]#
Index to connect to. | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-18 | field retriever: BaseRetriever [Required]#
Index to connect to.
classmethod from_llm(llm: langchain.schema.BaseLanguageModel, retriever: langchain.schema.BaseRetriever, condense_question_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['chat_history', 'question'], output_parser=None, partial_variables={}, template='Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.\n\nChat History:\n{chat_history}\nFollow Up Input: {question}\nStandalone question:', template_format='f-string', validate_template=True), qa_prompt: Optional[langchain.prompts.base.BasePromptTemplate] = None, chain_type: str = 'stuff', **kwargs: Any) → langchain.chains.conversational_retrieval.base.BaseConversationalRetrievalChain[source]#
Load chain from LLM.
pydantic model langchain.chains.GraphQAChain[source]#
Chain for question-answering against a graph.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field entity_extraction_chain: LLMChain [Required]#
field graph: NetworkxEntityGraph [Required]#
field qa_chain: LLMChain [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-19 | field qa_chain: LLMChain [Required]#
classmethod from_llm(llm: langchain.llms.base.BaseLLM, qa_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['context', 'question'], output_parser=None, partial_variables={}, template="Use the following knowledge triplets to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\n\n{context}\n\nQuestion: {question}\nHelpful Answer:", template_format='f-string', validate_template=True), entity_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['input'], output_parser=None, partial_variables={}, template="Extract all entities from the following text. As a guideline, a proper noun is generally capitalized. You should definitely extract all names and places.\n\nReturn the output as a single comma-separated list, or NONE if there is nothing of note to return.\n\nEXAMPLE\ni'm trying to improve Langchain's interfaces, the UX, its integrations with various products the user might want ... a lot of stuff.\nOutput: Langchain\nEND OF EXAMPLE\n\nEXAMPLE\ni'm trying to improve Langchain's interfaces, the UX, its integrations with various products the user might want ... a lot of stuff. I'm working with Sam.\nOutput: Langchain, Sam\nEND OF EXAMPLE\n\nBegin!\n\n{input}\nOutput:", template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.graph_qa.base.GraphQAChain[source]#
Initialize from LLM.
pydantic model langchain.chains.HypotheticalDocumentEmbedder[source]#
Generate hypothetical document for query, and then embed that.
Based on https://arxiv.org/abs/2212.10496
Validators
set_callback_manager » callback_manager | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-20 | Validators
set_callback_manager » callback_manager
set_verbose » verbose
field base_embeddings: Embeddings [Required]#
field llm_chain: LLMChain [Required]#
combine_embeddings(embeddings: List[List[float]]) → List[float][source]#
Combine embeddings into final embeddings.
embed_documents(texts: List[str]) → List[List[float]][source]#
Call the base embeddings.
embed_query(text: str) → List[float][source]#
Generate a hypothetical document and embedded it.
classmethod from_llm(llm: langchain.llms.base.BaseLLM, base_embeddings: langchain.embeddings.base.Embeddings, prompt_key: str) → langchain.chains.hyde.base.HypotheticalDocumentEmbedder[source]#
Load and use LLMChain for a specific prompt key.
property input_keys: List[str]#
Input keys for Hyde’s LLM chain.
property output_keys: List[str]#
Output keys for Hyde’s LLM chain.
pydantic model langchain.chains.LLMBashChain[source]#
Chain that interprets a prompt and executes bash code to perform bash operations.
Example
from langchain import LLMBashChain, OpenAI
llm_bash = LLMBashChain(llm=OpenAI())
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field llm: langchain.schema.BaseLanguageModel [Required]#
LLM wrapper to use. | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-21 | LLM wrapper to use.
field prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='If someone asks you to perform a task, your job is to come up with a series of bash commands that will perform the task. There is no need to put "#!/bin/bash" in your answer. Make sure to reason step by step, using this format:\n\nQuestion: "copy the files in the directory named \'target\' into a new directory at the same level as target called \'myNewDirectory\'"\n\nI need to take the following actions:\n- List all files in the directory\n- Create a new directory\n- Copy the files from the first directory into the second directory\n```bash\nls\nmkdir myNewDirectory\ncp -r target/* myNewDirectory\n```\n\nThat is the format. Begin!\n\nQuestion: {question}', template_format='f-string', validate_template=True)#
pydantic model langchain.chains.LLMChain[source]#
Chain to run queries against LLMs.
Example
from langchain import LLMChain, OpenAI, PromptTemplate
prompt_template = "Tell me a {adjective} joke"
prompt = PromptTemplate(
input_variables=["adjective"], template=prompt_template
)
llm = LLMChain(llm=OpenAI(), prompt=prompt)
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field llm: BaseLanguageModel [Required]#
field prompt: BasePromptTemplate [Required]#
Prompt object to use.
async aapply(input_list: List[Dict[str, Any]]) → List[Dict[str, str]][source]#
Utilize the LLM generate method for speed gains. | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-22 | Utilize the LLM generate method for speed gains.
async aapply_and_parse(input_list: List[Dict[str, Any]]) → Sequence[Union[str, List[str], Dict[str, str]]][source]#
Call apply and then parse the results.
async agenerate(input_list: List[Dict[str, Any]]) → langchain.schema.LLMResult[source]#
Generate LLM result from inputs.
apply(input_list: List[Dict[str, Any]]) → List[Dict[str, str]][source]#
Utilize the LLM generate method for speed gains.
apply_and_parse(input_list: List[Dict[str, Any]]) → Sequence[Union[str, List[str], Dict[str, str]]][source]#
Call apply and then parse the results.
async apredict(**kwargs: Any) → str[source]#
Format prompt with kwargs and pass to LLM.
Parameters
**kwargs – Keys to pass to prompt template.
Returns
Completion from LLM.
Example
completion = llm.predict(adjective="funny")
async apredict_and_parse(**kwargs: Any) → Union[str, List[str], Dict[str, str]][source]#
Call apredict and then parse the results.
async aprep_prompts(input_list: List[Dict[str, Any]]) → Tuple[List[langchain.schema.PromptValue], Optional[List[str]]][source]#
Prepare prompts from inputs.
create_outputs(response: langchain.schema.LLMResult) → List[Dict[str, str]][source]#
Create outputs from response.
classmethod from_string(llm: langchain.schema.BaseLanguageModel, template: str) → langchain.chains.base.Chain[source]#
Create LLMChain from LLM and template.
generate(input_list: List[Dict[str, Any]]) → langchain.schema.LLMResult[source]#
Generate LLM result from inputs. | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-23 | Generate LLM result from inputs.
predict(**kwargs: Any) → str[source]#
Format prompt with kwargs and pass to LLM.
Parameters
**kwargs – Keys to pass to prompt template.
Returns
Completion from LLM.
Example
completion = llm.predict(adjective="funny")
predict_and_parse(**kwargs: Any) → Union[str, List[str], Dict[str, str]][source]#
Call predict and then parse the results.
prep_prompts(input_list: List[Dict[str, Any]]) → Tuple[List[langchain.schema.PromptValue], Optional[List[str]]][source]#
Prepare prompts from inputs.
pydantic model langchain.chains.LLMCheckerChain[source]#
Chain for question-answering with self-verification.
Example
from langchain import OpenAI, LLMCheckerChain
llm = OpenAI(temperature=0.7)
checker_chain = LLMCheckerChain(llm=llm)
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field check_assertions_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['assertions'], output_parser=None, partial_variables={}, template='Here is a bullet point list of assertions:\n{assertions}\nFor each assertion, determine whether it is true or false. If it is false, explain why.\n\n', template_format='f-string', validate_template=True)#
field create_draft_answer_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='{question}\n\n', template_format='f-string', validate_template=True)# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-24 | field list_assertions_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['statement'], output_parser=None, partial_variables={}, template='Here is a statement:\n{statement}\nMake a bullet point list of the assumptions you made when producing the above statement.\n\n', template_format='f-string', validate_template=True)#
field llm: langchain.llms.base.BaseLLM [Required]#
LLM wrapper to use.
field revised_answer_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['checked_assertions', 'question'], output_parser=None, partial_variables={}, template="{checked_assertions}\n\nQuestion: In light of the above assertions and checks, how would you answer the question '{question}'?\n\nAnswer:", template_format='f-string', validate_template=True)#
Prompt to use when questioning the documents.
pydantic model langchain.chains.LLMMathChain[source]#
Chain that interprets a prompt and executes python code to do math.
Example
from langchain import LLMMathChain, OpenAI
llm_math = LLMMathChain(llm=OpenAI())
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field llm: langchain.schema.BaseLanguageModel [Required]#
LLM wrapper to use. | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-25 | LLM wrapper to use.
field prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='Translate a math problem into a expression that can be executed using Python\'s numexpr library. Use the output of running this code to answer the question.\n\nQuestion: ${{Question with math problem.}}\n```text\n${{single line mathematical expression that solves the problem}}\n```\n...numexpr.evaluate(text)...\n```output\n${{Output of running the code}}\n```\nAnswer: ${{Answer}}\n\nBegin.\n\nQuestion: What is 37593 * 67?\n\n```text\n37593 * 67\n```\n...numexpr.evaluate("37593 * 67")...\n```output\n2518731\n```\nAnswer: 2518731\n\nQuestion: {question}\n', template_format='f-string', validate_template=True)#
Prompt to use to translate to python if neccessary.
pydantic model langchain.chains.LLMRequestsChain[source]#
Chain that hits a URL and then uses an LLM to parse results.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_environment » all fields
field llm_chain: LLMChain [Required]#
field requests_wrapper: TextRequestsWrapper [Optional]#
field text_length: int = 8000#
pydantic model langchain.chains.LLMSummarizationCheckerChain[source]#
Chain for question-answering with self-verification.
Example
from langchain import OpenAI, LLMSummarizationCheckerChain
llm = OpenAI(temperature=0.0)
checker_chain = LLMSummarizationCheckerChain(llm=llm)
Validators
set_callback_manager » callback_manager | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-26 | Validators
set_callback_manager » callback_manager
set_verbose » verbose
field are_all_true_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['checked_assertions'], output_parser=None, partial_variables={}, template='Below are some assertions that have been fact checked and are labeled as true or false.\n\nIf all of the assertions are true, return "True". If any of the assertions are false, return "False".\n\nHere are some examples:\n===\n\nChecked Assertions: """\n- The sky is red: False\n- Water is made of lava: False\n- The sun is a star: True\n"""\nResult: False\n\n===\n\nChecked Assertions: """\n- The sky is blue: True\n- Water is wet: True\n- The sun is a star: True\n"""\nResult: True\n\n===\n\nChecked Assertions: """\n- The sky is blue - True\n- Water is made of lava- False\n- The sun is a star - True\n"""\nResult: False\n\n===\n\nChecked Assertions:"""\n{checked_assertions}\n"""\nResult:', template_format='f-string', validate_template=True)#
field check_assertions_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['assertions'], output_parser=None, partial_variables={}, template='You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.\n\nHere is a bullet point list of facts:\n"""\n{assertions}\n"""\n\nFor each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".\nIf the fact is false, explain why.\n\n', template_format='f-string', validate_template=True)# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-27 | field create_assertions_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['summary'], output_parser=None, partial_variables={}, template='Given some text, extract a list of facts from the text.\n\nFormat your output as a bulleted list.\n\nText:\n"""\n{summary}\n"""\n\nFacts:', template_format='f-string', validate_template=True)#
field llm: langchain.llms.base.BaseLLM [Required]#
LLM wrapper to use.
field max_checks: int = 2#
Maximum number of times to check the assertions. Default to double-checking.
field revised_summary_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['checked_assertions', 'summary'], output_parser=None, partial_variables={}, template='Below are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.\n\nChecked Assertions:\n"""\n{checked_assertions}\n"""\n\nOriginal Summary:\n"""\n{summary}\n"""\n\nUsing these checked assertions, rewrite the original summary to be completely true.\n\nThe output should have the same structure and formatting as the original summary.\n\nSummary:', template_format='f-string', validate_template=True)#
pydantic model langchain.chains.MapReduceChain[source]#
Map-reduce chain.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field combine_documents_chain: BaseCombineDocumentsChain [Required]#
Chain to use to combine documents.
field text_splitter: TextSplitter [Required]#
Text splitter to use. | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-28 | field text_splitter: TextSplitter [Required]#
Text splitter to use.
classmethod from_params(llm: langchain.llms.base.BaseLLM, prompt: langchain.prompts.base.BasePromptTemplate, text_splitter: langchain.text_splitter.TextSplitter) → langchain.chains.mapreduce.MapReduceChain[source]#
Construct a map-reduce chain that uses the chain for map and reduce.
pydantic model langchain.chains.OpenAIModerationChain[source]#
Pass input through a moderation endpoint.
To use, you should have the openai python package installed, and the
environment variable OPENAI_API_KEY set with your API key.
Any parameters that are valid to be passed to the openai.create call can be passed
in, even if not explicitly saved on this class.
Example
from langchain.chains import OpenAIModerationChain
moderation = OpenAIModerationChain()
Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_environment » all fields
field error: bool = False#
Whether or not to error if bad content was found.
field model_name: Optional[str] = None#
Moderation model name to use.
field openai_api_key: Optional[str] = None#
field openai_organization: Optional[str] = None#
pydantic model langchain.chains.OpenAPIEndpointChain[source]#
Chain interacts with an OpenAPI endpoint using natural language.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field api_operation: APIOperation [Required]#
field api_request_chain: LLMChain [Required]#
field api_response_chain: Optional[LLMChain] = None#
field param_mapping: _ParamMapping [Required]#
field requests: Requests [Optional]#
field return_intermediate_steps: bool = False# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-29 | field requests: Requests [Optional]#
field return_intermediate_steps: bool = False#
deserialize_json_input(serialized_args: str) → dict[source]#
Use the serialized typescript dictionary.
Resolve the path, query params dict, and optional requestBody dict.
classmethod from_api_operation(operation: langchain.tools.openapi.utils.api_models.APIOperation, llm: langchain.llms.base.BaseLLM, requests: Optional[langchain.requests.Requests] = None, verbose: bool = False, return_intermediate_steps: bool = False, raw_response: bool = False, **kwargs: Any) → OpenAPIEndpointChain[source]#
Create an OpenAPIEndpointChain from an operation and a spec.
classmethod from_url_and_method(spec_url: str, path: str, method: str, llm: langchain.llms.base.BaseLLM, requests: Optional[langchain.requests.Requests] = None, return_intermediate_steps: bool = False, **kwargs: Any) → OpenAPIEndpointChain[source]#
Create an OpenAPIEndpoint from a spec at the specified url.
pydantic model langchain.chains.PALChain[source]#
Implements Program-Aided Language Models.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field get_answer_expr: str = 'print(solution())'#
field llm: BaseLanguageModel [Required]#
field prompt: BasePromptTemplate [Required]#
field python_globals: Optional[Dict[str, Any]] = None#
field python_locals: Optional[Dict[str, Any]] = None#
field return_intermediate_steps: bool = False#
field stop: str = '\n\n'#
classmethod from_colored_object_prompt(llm: langchain.schema.BaseLanguageModel, **kwargs: Any) → langchain.chains.pal.base.PALChain[source]#
Load PAL from colored object prompt. | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-30 | Load PAL from colored object prompt.
classmethod from_math_prompt(llm: langchain.schema.BaseLanguageModel, **kwargs: Any) → langchain.chains.pal.base.PALChain[source]#
Load PAL from math prompt.
pydantic model langchain.chains.QAGenerationChain[source]#
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field input_key: str = 'text'#
field k: Optional[int] = None#
field llm_chain: LLMChain [Required]#
field output_key: str = 'questions'#
field text_splitter: TextSplitter = <langchain.text_splitter.RecursiveCharacterTextSplitter object>#
classmethod from_llm(llm: langchain.schema.BaseLanguageModel, prompt: Optional[langchain.prompts.base.BasePromptTemplate] = None, **kwargs: Any) → langchain.chains.qa_generation.base.QAGenerationChain[source]#
property input_keys: List[str]#
Input keys this chain expects.
property output_keys: List[str]#
Output keys this chain expects.
pydantic model langchain.chains.QAWithSourcesChain[source]#
Question answering with sources over documents.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_naming » all fields
pydantic model langchain.chains.RetrievalQA[source]#
Chain for question-answering against an index.
Example
from langchain.llms import OpenAI
from langchain.chains import RetrievalQA
from langchain.faiss import FAISS
from langchain.vectorstores.base import VectorStoreRetriever
retriever = VectorStoreRetriever(vectorstore=FAISS(...))
retrievalQA = RetrievalQA.from_llm(llm=OpenAI(), retriever=retriever)
Validators
set_callback_manager » callback_manager | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-31 | Validators
set_callback_manager » callback_manager
set_verbose » verbose
field retriever: BaseRetriever [Required]#
pydantic model langchain.chains.RetrievalQAWithSourcesChain[source]#
Question-answering with sources over an index.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_naming » all fields
field max_tokens_limit: int = 3375#
Restrict the docs to return from store based on tokens,
enforced only for StuffDocumentChain and if reduce_k_below_max_tokens is to true
field reduce_k_below_max_tokens: bool = False#
Reduce the number of results to return from store based on tokens limit
field retriever: langchain.schema.BaseRetriever [Required]#
Index to connect to.
pydantic model langchain.chains.SQLDatabaseChain[source]#
Chain for interacting with SQL Database.
Example
from langchain import SQLDatabaseChain, OpenAI, SQLDatabase
db = SQLDatabase(...)
db_chain = SQLDatabaseChain(llm=OpenAI(), database=db)
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field database: SQLDatabase [Required]#
SQL Database to connect to.
field llm: BaseLanguageModel [Required]#
LLM wrapper to use.
field prompt: Optional[BasePromptTemplate] = None#
Prompt to use to translate natural language to SQL.
field return_direct: bool = False#
Whether or not to return the result of querying the SQL table directly.
field return_intermediate_steps: bool = False#
Whether or not to return the intermediate steps along with the final answer.
field top_k: int = 5#
Number of results to return from the query
pydantic model langchain.chains.SQLDatabaseSequentialChain[source]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-32 | pydantic model langchain.chains.SQLDatabaseSequentialChain[source]#
Chain for querying SQL database that is a sequential chain.
The chain is as follows:
1. Based on the query, determine which tables to use.
2. Based on those tables, call the normal SQL database chain.
This is useful in cases where the number of tables in the database is large.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field decider_chain: LLMChain [Required]#
field return_intermediate_steps: bool = False#
field sql_chain: SQLDatabaseChain [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-33 | classmethod from_llm(llm: langchain.schema.BaseLanguageModel, database: langchain.sql_database.SQLDatabase, query_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['input', 'table_info', 'dialect', 'top_k'], output_parser=None, partial_variables={}, template='Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer. Unless the user specifies in his question a specific number of examples he wishes to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.\n\nNever query for all the columns from a specific table, only ask for a the few relevant columns given the question.\n\nPay attention to use only the column names that you can see in the schema description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.\n\nUse the following format:\n\nQuestion: "Question here"\nSQLQuery: "SQL Query to run"\nSQLResult: "Result of the | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-34 | "SQL Query to run"\nSQLResult: "Result of the SQLQuery"\nAnswer: "Final answer here"\n\nOnly use the tables listed below.\n\n{table_info}\n\nQuestion: {input}', template_format='f-string', validate_template=True), decider_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['query', 'table_names'], output_parser=CommaSeparatedListOutputParser(), partial_variables={}, template='Given the below input question and list of potential tables, output a comma separated list of the table names that may be necessary to answer this question.\n\nQuestion: {query}\n\nTable Names: {table_names}\n\nRelevant Table Names:', template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.sql_database.base.SQLDatabaseSequentialChain[source]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-35 | Load the necessary chains.
pydantic model langchain.chains.SequentialChain[source]#
Chain where the outputs of one chain feed directly into next.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_chains » all fields
field chains: List[langchain.chains.base.Chain] [Required]#
field input_variables: List[str] [Required]#
field return_all: bool = False#
pydantic model langchain.chains.SimpleSequentialChain[source]#
Simple chain where the outputs of one step feed directly into next.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_chains » all fields
field chains: List[langchain.chains.base.Chain] [Required]#
field strip_outputs: bool = False#
pydantic model langchain.chains.TransformChain[source]#
Chain transform chain output.
Example
from langchain import TransformChain
transform_chain = TransformChain(input_variables=["text"],
output_variables["entities"], transform=func())
Validators
set_callback_manager » callback_manager
set_verbose » verbose
field input_variables: List[str] [Required]#
field output_variables: List[str] [Required]#
field transform: Callable[[Dict[str, str]], Dict[str, str]] [Required]#
pydantic model langchain.chains.VectorDBQA[source]#
Chain for question-answering against a vector database.
Validators
raise_deprecation » all fields
set_callback_manager » callback_manager
set_verbose » verbose
validate_search_type » all fields
field k: int = 4#
Number of documents to query for.
field search_kwargs: Dict[str, Any] [Optional]#
Extra search args.
field search_type: str = 'similarity'#
Search type to use over vectorstore. similarity or mmr. | https://python.langchain.com/en/latest/reference/modules/chains.html |
3c17d3dd911f-36 | Search type to use over vectorstore. similarity or mmr.
field vectorstore: VectorStore [Required]#
Vector Database to connect to.
pydantic model langchain.chains.VectorDBQAWithSourcesChain[source]#
Question-answering with sources over a vector database.
Validators
raise_deprecation » all fields
set_callback_manager » callback_manager
set_verbose » verbose
validate_naming » all fields
field k: int = 4#
Number of results to return from store
field max_tokens_limit: int = 3375#
Restrict the docs to return from store based on tokens,
enforced only for StuffDocumentChain and if reduce_k_below_max_tokens is to true
field reduce_k_below_max_tokens: bool = False#
Reduce the number of results to return from store based on tokens limit
field search_kwargs: Dict[str, Any] [Optional]#
Extra search args.
field vectorstore: langchain.vectorstores.base.VectorStore [Required]#
Vector Database to connect to.
langchain.chains.load_chain(path: Union[str, pathlib.Path], **kwargs: Any) → langchain.chains.base.Chain[source]#
Unified method for loading a chain from LangChainHub or local fs.
previous
SQL Chain example
next
Agents
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 21, 2023. | https://python.langchain.com/en/latest/reference/modules/chains.html |
9c4a218da040-0 | .rst
.pdf
Agents
Agents#
Interface for agents.
pydantic model langchain.agents.Agent[source]#
Class responsible for calling the language model and deciding the action.
This is driven by an LLMChain. The prompt in the LLMChain MUST include
a variable called “agent_scratchpad” where the agent can put its
intermediary work.
field allowed_tools: Optional[List[str]] = None#
field llm_chain: langchain.chains.llm.LLMChain [Required]#
field output_parser: langchain.agents.agent.AgentOutputParser [Required]#
async aplan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
**kwargs – User inputs.
Returns
Action specifying what tool to use.
abstract classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool]) → langchain.prompts.base.BasePromptTemplate[source]#
Create a prompt for this class.
classmethod from_llm_and_tools(llm: langchain.schema.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, output_parser: Optional[langchain.agents.agent.AgentOutputParser] = None, **kwargs: Any) → langchain.agents.agent.Agent[source]#
Construct an agent from an LLM and tools.
get_allowed_tools() → Optional[List[str]][source]#
get_full_inputs(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → Dict[str, Any][source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-1 | Create the full inputs for the LLMChain from intermediate steps.
plan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
**kwargs – User inputs.
Returns
Action specifying what tool to use.
return_stopped_response(early_stopping_method: str, intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → langchain.schema.AgentFinish[source]#
Return response when agent has been stopped due to max iterations.
tool_run_logging_kwargs() → Dict[source]#
abstract property llm_prefix: str#
Prefix to append the LLM call with.
abstract property observation_prefix: str#
Prefix to append the observation with.
property return_values: List[str]#
Return values of the agent.
pydantic model langchain.agents.AgentExecutor[source]#
Consists of an agent using tools.
Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_return_direct_tool » all fields
validate_tools » all fields
field agent: Union[BaseSingleActionAgent, BaseMultiActionAgent] [Required]#
field early_stopping_method: str = 'force'#
field max_execution_time: Optional[float] = None#
field max_iterations: Optional[int] = 15#
field return_intermediate_steps: bool = False#
field tools: Sequence[BaseTool] [Required]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-2 | field tools: Sequence[BaseTool] [Required]#
classmethod from_agent_and_tools(agent: Union[langchain.agents.agent.BaseSingleActionAgent, langchain.agents.agent.BaseMultiActionAgent], tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]#
Create from agent and tools.
lookup_tool(name: str) → langchain.tools.base.BaseTool[source]#
Lookup tool by name.
save(file_path: Union[pathlib.Path, str]) → None[source]#
Raise error - saving not supported for Agent Executors.
save_agent(file_path: Union[pathlib.Path, str]) → None[source]#
Save the underlying agent.
pydantic model langchain.agents.AgentOutputParser[source]#
abstract parse(text: str) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Parse text into agent action/finish.
class langchain.agents.AgentType(value)[source]#
An enumeration.
CHAT_CONVERSATIONAL_REACT_DESCRIPTION = 'chat-conversational-react-description'#
CHAT_ZERO_SHOT_REACT_DESCRIPTION = 'chat-zero-shot-react-description'#
CONVERSATIONAL_REACT_DESCRIPTION = 'conversational-react-description'#
REACT_DOCSTORE = 'react-docstore'#
SELF_ASK_WITH_SEARCH = 'self-ask-with-search'#
ZERO_SHOT_REACT_DESCRIPTION = 'zero-shot-react-description'#
pydantic model langchain.agents.BaseMultiActionAgent[source]#
Base Agent class.
abstract async aplan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → Union[List[langchain.schema.AgentAction], langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-3 | Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
**kwargs – User inputs.
Returns
Actions specifying what tool to use.
dict(**kwargs: Any) → Dict[source]#
Return dictionary representation of agent.
get_allowed_tools() → Optional[List[str]][source]#
abstract plan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → Union[List[langchain.schema.AgentAction], langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
**kwargs – User inputs.
Returns
Actions specifying what tool to use.
return_stopped_response(early_stopping_method: str, intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → langchain.schema.AgentFinish[source]#
Return response when agent has been stopped due to max iterations.
save(file_path: Union[pathlib.Path, str]) → None[source]#
Save the agent.
Parameters
file_path – Path to file to save the agent to.
Example:
.. code-block:: python
# If working with agent executor
agent.agent.save(file_path=”path/agent.yaml”)
tool_run_logging_kwargs() → Dict[source]#
property return_values: List[str]#
Return values of the agent.
pydantic model langchain.agents.BaseSingleActionAgent[source]#
Base Agent class.
abstract async aplan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-4 | Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
**kwargs – User inputs.
Returns
Action specifying what tool to use.
dict(**kwargs: Any) → Dict[source]#
Return dictionary representation of agent.
classmethod from_llm_and_tools(llm: langchain.schema.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, **kwargs: Any) → langchain.agents.agent.BaseSingleActionAgent[source]#
get_allowed_tools() → Optional[List[str]][source]#
abstract plan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
**kwargs – User inputs.
Returns
Action specifying what tool to use.
return_stopped_response(early_stopping_method: str, intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → langchain.schema.AgentFinish[source]#
Return response when agent has been stopped due to max iterations.
save(file_path: Union[pathlib.Path, str]) → None[source]#
Save the agent.
Parameters
file_path – Path to file to save the agent to.
Example:
.. code-block:: python
# If working with agent executor
agent.agent.save(file_path=”path/agent.yaml”)
tool_run_logging_kwargs() → Dict[source]#
property return_values: List[str]#
Return values of the agent.
pydantic model langchain.agents.ConversationalAgent[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-5 | pydantic model langchain.agents.ConversationalAgent[source]#
An agent designed to hold a conversation in addition to using tools.
field ai_prefix: str = 'AI'#
field output_parser: langchain.agents.agent.AgentOutputParser [Optional]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-6 | classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool], prefix: str = 'Assistant is a large language model trained by OpenAI.\n\nAssistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n\nAssistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n\nOverall, Assistant is a powerful tool that can help with a wide range of | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-7 | powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n\nTOOLS:\n------\n\nAssistant has access to the following tools:', suffix: str = 'Begin!\n\nPrevious conversation history:\n{chat_history}\n\nNew input: {input}\n{agent_scratchpad}', format_instructions: str = 'To use a tool, please use the following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response to say to the Human, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\n{ai_prefix}: [your response here]\n```', ai_prefix: str = 'AI', human_prefix: str = 'Human', input_variables: | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-8 | 'AI', human_prefix: str = 'Human', input_variables: Optional[List[str]] = None) → langchain.prompts.prompt.PromptTemplate[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-9 | Create prompt in the style of the zero shot agent.
Parameters
tools – List of tools the agent will have access to, used to format the
prompt.
prefix – String to put before the list of tools.
suffix – String to put after the list of tools.
ai_prefix – String to use before AI output.
human_prefix – String to use before human output.
input_variables – List of input variables the final prompt will expect.
Returns
A PromptTemplate with the template assembled from the pieces here. | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-10 | classmethod from_llm_and_tools(llm: langchain.schema.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, output_parser: Optional[langchain.agents.agent.AgentOutputParser] = None, prefix: str = 'Assistant is a large language model trained by OpenAI.\n\nAssistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n\nAssistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-11 | receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n\nOverall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n\nTOOLS:\n------\n\nAssistant has access to the following tools:', suffix: str = 'Begin!\n\nPrevious conversation history:\n{chat_history}\n\nNew input: {input}\n{agent_scratchpad}', format_instructions: str = 'To use a tool, please use the following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response to say to the Human, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-12 | the format:\n\n```\nThought: Do I need to use a tool? No\n{ai_prefix}: [your response here]\n```', ai_prefix: str = 'AI', human_prefix: str = 'Human', input_variables: Optional[List[str]] = None, **kwargs: Any) → langchain.agents.agent.Agent[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-13 | Construct an agent from an LLM and tools.
property llm_prefix: str#
Prefix to append the llm call with.
property observation_prefix: str#
Prefix to append the observation with.
pydantic model langchain.agents.ConversationalChatAgent[source]#
An agent designed to hold a conversation in addition to using tools.
field output_parser: langchain.agents.agent.AgentOutputParser [Optional]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-14 | classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool], system_message: str = 'Assistant is a large language model trained by OpenAI.\n\nAssistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n\nAssistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n\nOverall, Assistant is a powerful system that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.', human_message: str = "TOOLS\n------\nAssistant can ask the user to use tools to look up information that may be helpful in answering the users original question. The tools the human can use are:\n\n{{tools}}\n\n{format_instructions}\n\nUSER'S INPUT\n--------------------\nHere is the user's input (remember to respond with a markdown code snippet of a json blob with a single action, and NOTHING else):\n\n{{{{input}}}}", input_variables: Optional[List[str]] = None, output_parser: Optional[langchain.schema.BaseOutputParser] = None) → langchain.prompts.base.BasePromptTemplate[source]#
Create a prompt for this class. | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-15 | classmethod from_llm_and_tools(llm: langchain.schema.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, output_parser: Optional[langchain.agents.agent.AgentOutputParser] = None, system_message: str = 'Assistant is a large language model trained by OpenAI.\n\nAssistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n\nAssistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-16 | receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n\nOverall, Assistant is a powerful system that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.', human_message: str = "TOOLS\n------\nAssistant can ask the user to use tools to look up information that may be helpful in answering the users original question. The tools the human can use are:\n\n{{tools}}\n\n{format_instructions}\n\nUSER'S INPUT\n--------------------\nHere is the user's input (remember to respond with a markdown code snippet of a json blob with a single action, and NOTHING else):\n\n{{{{input}}}}", input_variables: Optional[List[str]] = None, **kwargs: Any) → langchain.agents.agent.Agent[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-17 | Construct an agent from an LLM and tools.
property llm_prefix: str#
Prefix to append the llm call with.
property observation_prefix: str#
Prefix to append the observation with.
pydantic model langchain.agents.LLMSingleActionAgent[source]#
field llm_chain: langchain.chains.llm.LLMChain [Required]#
field output_parser: langchain.agents.agent.AgentOutputParser [Required]#
field stop: List[str] [Required]#
async aplan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
**kwargs – User inputs.
Returns
Action specifying what tool to use.
plan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
**kwargs – User inputs.
Returns
Action specifying what tool to use.
tool_run_logging_kwargs() → Dict[source]#
pydantic model langchain.agents.MRKLChain[source]#
Chain that implements the MRKL system.
Example
from langchain import OpenAI, MRKLChain
from langchain.chains.mrkl.base import ChainConfig
llm = OpenAI(temperature=0)
prompt = PromptTemplate(...)
chains = [...]
mrkl = MRKLChain.from_chains(llm=llm, prompt=prompt)
Validators
set_callback_manager » callback_manager | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-18 | Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_return_direct_tool » all fields
validate_tools » all fields
field agent: Union[BaseSingleActionAgent, BaseMultiActionAgent] [Required]#
field callback_manager: BaseCallbackManager [Optional]#
field early_stopping_method: str = 'force'#
field max_execution_time: Optional[float] = None#
field max_iterations: Optional[int] = 15#
field memory: Optional[BaseMemory] = None#
field return_intermediate_steps: bool = False#
field tools: Sequence[BaseTool] [Required]#
field verbose: bool [Optional]#
classmethod from_chains(llm: langchain.schema.BaseLanguageModel, chains: List[langchain.agents.mrkl.base.ChainConfig], **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]#
User friendly way to initialize the MRKL chain.
This is intended to be an easy way to get up and running with the
MRKL chain.
Parameters
llm – The LLM to use as the agent LLM.
chains – The chains the MRKL system has access to.
**kwargs – parameters to be passed to initialization.
Returns
An initialized MRKL chain.
Example
from langchain import LLMMathChain, OpenAI, SerpAPIWrapper, MRKLChain
from langchain.chains.mrkl.base import ChainConfig
llm = OpenAI(temperature=0)
search = SerpAPIWrapper()
llm_math_chain = LLMMathChain(llm=llm)
chains = [
ChainConfig(
action_name = "Search",
action=search.search,
action_description="useful for searching"
),
ChainConfig(
action_name="Calculator",
action=llm_math_chain.run, | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-19 | action_name="Calculator",
action=llm_math_chain.run,
action_description="useful for doing math"
)
]
mrkl = MRKLChain.from_chains(llm, chains)
pydantic model langchain.agents.ReActChain[source]#
Chain that implements the ReAct paper.
Example
from langchain import ReActChain, OpenAI
react = ReAct(llm=OpenAI())
Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_return_direct_tool » all fields
validate_tools » all fields
field agent: Union[BaseSingleActionAgent, BaseMultiActionAgent] [Required]#
field callback_manager: BaseCallbackManager [Optional]#
field early_stopping_method: str = 'force'#
field max_execution_time: Optional[float] = None#
field max_iterations: Optional[int] = 15#
field memory: Optional[BaseMemory] = None#
field return_intermediate_steps: bool = False#
field tools: Sequence[BaseTool] [Required]#
field verbose: bool [Optional]#
pydantic model langchain.agents.ReActTextWorldAgent[source]#
Agent for the ReAct TextWorld chain.
field output_parser: langchain.agents.agent.AgentOutputParser [Optional]#
classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool]) → langchain.prompts.base.BasePromptTemplate[source]#
Return default prompt.
pydantic model langchain.agents.SelfAskWithSearchChain[source]#
Chain that does self ask with search.
Example
from langchain import SelfAskWithSearchChain, OpenAI, GoogleSerperAPIWrapper
search_chain = GoogleSerperAPIWrapper()
self_ask = SelfAskWithSearchChain(llm=OpenAI(), search_chain=search_chain)
Validators
set_callback_manager » callback_manager | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-20 | Validators
set_callback_manager » callback_manager
set_verbose » verbose
validate_return_direct_tool » all fields
validate_tools » all fields
field agent: Union[BaseSingleActionAgent, BaseMultiActionAgent] [Required]#
field callback_manager: BaseCallbackManager [Optional]#
field early_stopping_method: str = 'force'#
field max_execution_time: Optional[float] = None#
field max_iterations: Optional[int] = 15#
field memory: Optional[BaseMemory] = None#
field return_intermediate_steps: bool = False#
field tools: Sequence[BaseTool] [Required]#
field verbose: bool [Optional]#
pydantic model langchain.agents.Tool[source]#
Tool that takes in function or coroutine directly.
Validators
set_callback_manager » callback_manager
field coroutine: Optional[Callable[[...], Awaitable[str]]] = None#
The asynchronous version of the function.
field description: str = ''#
field func: Callable[[...], str] [Required]#
The function to run when the tool is called.
property args: dict#
pydantic model langchain.agents.ZeroShotAgent[source]#
Agent for the MRKL chain.
field output_parser: langchain.agents.agent.AgentOutputParser [Optional]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-21 | field output_parser: langchain.agents.agent.AgentOutputParser [Optional]#
classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool], prefix: str = 'Answer the following questions as best you can. You have access to the following tools:', suffix: str = 'Begin!\n\nQuestion: {input}\nThought:{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: Optional[List[str]] = None) → langchain.prompts.prompt.PromptTemplate[source]#
Create prompt in the style of the zero shot agent.
Parameters
tools – List of tools the agent will have access to, used to format the
prompt.
prefix – String to put before the list of tools.
suffix – String to put after the list of tools.
input_variables – List of input variables the final prompt will expect.
Returns
A PromptTemplate with the template assembled from the pieces here. | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-22 | Returns
A PromptTemplate with the template assembled from the pieces here.
classmethod from_llm_and_tools(llm: langchain.schema.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, output_parser: Optional[langchain.agents.agent.AgentOutputParser] = None, prefix: str = 'Answer the following questions as best you can. You have access to the following tools:', suffix: str = 'Begin!\n\nQuestion: {input}\nThought:{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: Optional[List[str]] = None, **kwargs: Any) → langchain.agents.agent.Agent[source]#
Construct an agent from an LLM and tools.
property llm_prefix: str#
Prefix to append the llm call with.
property observation_prefix: str#
Prefix to append the observation with.
langchain.agents.create_csv_agent(llm: langchain.llms.base.BaseLLM, path: str, pandas_kwargs: Optional[dict] = None, **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]#
Create csv agent by loading to a dataframe and using pandas agent. | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-23 | langchain.agents.create_json_agent(llm: langchain.llms.base.BaseLLM, toolkit: langchain.agents.agent_toolkits.json.toolkit.JsonToolkit, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = 'You are an agent designed to interact with JSON.\nYour goal is to return a final answer by interacting with the JSON.\nYou have access to the following tools which help you learn more about the JSON you are interacting with.\nOnly use the below tools. Only use the information returned by the below tools to construct your final answer.\nDo not make up any information that is not contained in the JSON.\nYour input to the tools should be in the form of `data["key"][0]` where `data` is the JSON blob you are interacting with, and the syntax used is Python. \nYou should only use keys that you know for a fact exist. You must validate that a key exists by seeing it previously when calling `json_spec_list_keys`. \nIf you have not seen a key in one of those responses, you cannot use it.\nYou should only add one key at | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-24 | cannot use it.\nYou should only add one key at a time to the path. You cannot add multiple keys at once.\nIf you encounter a "KeyError", go back to the previous key, look at the available keys, and try again.\n\nIf the question does not seem to be related to the JSON, just return "I don\'t know" as the answer.\nAlways begin your interaction with the `json_spec_list_keys` tool with input "data" to see what keys exist in the JSON.\n\nNote that sometimes the value at a given path is large. In this case, you will get an error "Value is a large dictionary, should explore its keys directly".\nIn this case, you should ALWAYS follow up by using the `json_spec_list_keys` tool to see what keys exist at that path.\nDo not simply refer the user to the JSON or a section of the JSON, as this is not a valid answer. Keep digging until you find the answer and explicitly return it.\n', suffix: str = 'Begin!"\n\nQuestion: {input}\nThought: I | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-25 | = 'Begin!"\n\nQuestion: {input}\nThought: I should look at the keys that exist in data to see what I have access to\n{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: Optional[List[str]] = None, verbose: bool = False, **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-26 | Construct a json agent from an LLM and tools. | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-27 | langchain.agents.create_openapi_agent(llm: langchain.llms.base.BaseLLM, toolkit: langchain.agents.agent_toolkits.openapi.toolkit.OpenAPIToolkit, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = "You are an agent designed to answer questions by making web requests to an API given the openapi spec.\n\nIf the question does not seem related to the API, return I don't know. Do not make up an answer.\nOnly use information provided by the tools to construct your response.\n\nFirst, find the base URL needed to make the request.\n\nSecond, find the relevant paths needed to answer the question. Take note that, sometimes, you might need to make more than one request to more than one path to answer the question.\n\nThird, find the required parameters needed to make the request. For GET requests, these are usually URL parameters and for POST requests, these are request body parameters.\n\nFourth, make the requests needed to answer the question. Ensure that you are sending the correct parameters to the request by checking which parameters are required. For parameters with a fixed set | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-28 | which parameters are required. For parameters with a fixed set of values, please use the spec to look at which values are allowed.\n\nUse the exact parameter names as listed in the spec, do not make up any names or abbreviate the names of parameters.\nIf you get a not found error, ensure that you are using a path that actually exists in the spec.\n", suffix: str = 'Begin!\n\nQuestion: {input}\nThought: I should explore the spec to find the base url for the API.\n{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: Optional[List[str]] = None, max_iterations: Optional[int] = 15, max_execution_time: | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-29 | None, max_iterations: Optional[int] = 15, max_execution_time: Optional[float] = None, early_stopping_method: str = 'force', verbose: bool = False, return_intermediate_steps: bool = False, **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-30 | Construct a json agent from an LLM and tools.
langchain.agents.create_pandas_dataframe_agent(llm: langchain.llms.base.BaseLLM, df: Any, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = '\nYou are working with a pandas dataframe in Python. The name of the dataframe is `df`.\nYou should use the tools below to answer the question posed of you:', suffix: str = '\nThis is the result of `print(df.head())`:\n{df}\n\nBegin!\nQuestion: {input}\n{agent_scratchpad}', input_variables: Optional[List[str]] = None, verbose: bool = False, return_intermediate_steps: bool = False, max_iterations: Optional[int] = 15, max_execution_time: Optional[float] = None, early_stopping_method: str = 'force', **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]#
Construct a pandas agent from an LLM and dataframe. | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-31 | langchain.agents.create_sql_agent(llm: langchain.llms.base.BaseLLM, toolkit: langchain.agents.agent_toolkits.sql.toolkit.SQLDatabaseToolkit, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = 'You are an agent designed to interact with a SQL database.\nGiven an input question, create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer.\nUnless the user specifies a specific number of examples they wish to obtain, always limit your query to at most {top_k} results.\nYou can order the results by a relevant column to return the most interesting examples in the database.\nNever query for all the columns from a specific table, only ask for the relevant columns given the question.\nYou have access to tools for interacting with the database.\nOnly use the below tools. Only use the information returned by the below tools to construct your final answer.\nYou MUST double check your query before executing it. If you get an error while executing a query, rewrite the query and try again.\n\nDO NOT make | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-32 | rewrite the query and try again.\n\nDO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the database.\n\nIf the question does not seem related to the database, just return "I don\'t know" as the answer.\n', suffix: str = 'Begin!\n\nQuestion: {input}\nThought: I should look at the tables in the database to see what I can query.\n{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: Optional[List[str]] = None, top_k: int = 10, max_iterations: Optional[int] = 15, max_execution_time: Optional[float] = None, early_stopping_method: str = 'force', verbose: bool = False, | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-33 | str = 'force', verbose: bool = False, **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-34 | Construct a sql agent from an LLM and tools.
langchain.agents.create_vectorstore_agent(llm: langchain.llms.base.BaseLLM, toolkit: langchain.agents.agent_toolkits.vectorstore.toolkit.VectorStoreToolkit, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = 'You are an agent designed to answer questions about sets of documents.\nYou have access to tools for interacting with the documents, and the inputs to the tools are questions.\nSometimes, you will be asked to provide sources for your questions, in which case you should use the appropriate tool to do so.\nIf the question does not seem relevant to any of the tools provided, just return "I don\'t know" as the answer.\n', verbose: bool = False, **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]#
Construct a vectorstore agent from an LLM and tools.
langchain.agents.create_vectorstore_router_agent(llm: langchain.llms.base.BaseLLM, toolkit: langchain.agents.agent_toolkits.vectorstore.toolkit.VectorStoreRouterToolkit, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = 'You are an agent designed to answer questions.\nYou have access to tools for interacting with different sources, and the inputs to the tools are questions.\nYour main task is to decide which of the tools is relevant for answering question at hand.\nFor complex questions, you can break the question down into sub questions and use tools to answers the sub questions.\n', verbose: bool = False, **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]#
Construct a vectorstore router agent from an LLM and tools.
langchain.agents.get_all_tool_names() → List[str][source]#
Get a list of all possible tool names. | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-35 | Get a list of all possible tool names.
langchain.agents.initialize_agent(tools: Sequence[langchain.tools.base.BaseTool], llm: langchain.schema.BaseLanguageModel, agent: Optional[langchain.agents.agent_types.AgentType] = None, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, agent_path: Optional[str] = None, agent_kwargs: Optional[dict] = None, **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]#
Load an agent executor given tools and LLM.
Parameters
tools – List of tools this agent has access to.
llm – Language model to use as the agent.
agent – Agent type to use. If None and agent_path is also None, will default to
AgentType.ZERO_SHOT_REACT_DESCRIPTION.
callback_manager – CallbackManager to use. Global callback manager is used if
not provided. Defaults to None.
agent_path – Path to serialized agent to use.
agent_kwargs – Additional key word arguments to pass to the underlying agent
**kwargs – Additional key word arguments passed to the agent executor
Returns
An agent executor
langchain.agents.load_agent(path: Union[str, pathlib.Path], **kwargs: Any) → langchain.agents.agent.BaseSingleActionAgent[source]#
Unified method for loading a agent from LangChainHub or local fs.
langchain.agents.load_tools(tool_names: List[str], llm: Optional[langchain.llms.base.BaseLLM] = None, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, **kwargs: Any) → List[langchain.tools.base.BaseTool][source]#
Load tools based on their name.
Parameters
tool_names – name of tools to load.
llm – Optional language model, may be needed to initialize certain tools. | https://python.langchain.com/en/latest/reference/modules/agents.html |
9c4a218da040-36 | llm – Optional language model, may be needed to initialize certain tools.
callback_manager – Optional callback manager. If not provided, default global callback manager will be used.
Returns
List of tools.
langchain.agents.tool(*args: Union[str, Callable], return_direct: bool = False, args_schema: Optional[Type[pydantic.main.BaseModel]] = None, infer_schema: bool = True) → Callable[source]#
Make tools out of functions, can be used with or without arguments.
Parameters
*args – The arguments to the tool.
return_direct – Whether to return directly from the tool rather
than continuing the agent loop.
args_schema – optional argument schema for user to specify
infer_schema – Whether to infer the schema of the arguments from
the function’s signature. This also makes the resultant tool
accept a dictionary input to its run() function.
Requires:
Function must be of type (str) -> str
Function must have a docstring
Examples
@tool
def search_api(query: str) -> str:
# Searches the API for the query.
return
@tool("search", return_direct=True)
def search_api(query: str) -> str:
# Searches the API for the query.
return
previous
VectorStores
next
LangChain Ecosystem
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 21, 2023. | https://python.langchain.com/en/latest/reference/modules/agents.html |
c0587b89c087-0 | .rst
.pdf
Python REPL
Python REPL#
For backwards compatibility.
pydantic model langchain.python.PythonREPL[source]#
Simulates a standalone Python REPL.
field globals: Optional[Dict] [Optional] (alias '_globals')#
field locals: Optional[Dict] [Optional] (alias '_locals')#
run(command: str) → str[source]#
Run command with own globals/locals and returns anything printed.
previous
Utilities
next
SerpAPI
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Apr 21, 2023. | https://python.langchain.com/en/latest/reference/modules/python.html |
cc47f48085d0-0 | .rst
.pdf
Embeddings
Embeddings#
Wrappers around embedding modules.
pydantic model langchain.embeddings.AlephAlphaAsymmetricSemanticEmbedding[source]#
Wrapper for Aleph Alpha’s Asymmetric Embeddings
AA provides you with an endpoint to embed a document and a query.
The models were optimized to make the embeddings of documents and
the query for a document as similar as possible.
To learn more, check out: https://docs.aleph-alpha.com/docs/tasks/semantic_embed/
Example
from aleph_alpha import AlephAlphaAsymmetricSemanticEmbedding
embeddings = AlephAlphaSymmetricSemanticEmbedding()
document = "This is a content of the document"
query = "What is the content of the document?"
doc_result = embeddings.embed_documents([document])
query_result = embeddings.embed_query(query)
field compress_to_size: Optional[int] = 128#
Should the returned embeddings come back as an original 5120-dim vector,
or should it be compressed to 128-dim.
field contextual_control_threshold: Optional[int] = None#
Attention control parameters only apply to those tokens that have
explicitly been set in the request.
field control_log_additive: Optional[bool] = True#
Apply controls on prompt items by adding the log(control_factor)
to attention scores.
field hosting: Optional[str] = 'https://api.aleph-alpha.com'#
Optional parameter that specifies which datacenters may process the request.
field model: Optional[str] = 'luminous-base'#
Model name to use.
field normalize: Optional[bool] = True#
Should returned embeddings be normalized
embed_documents(texts: List[str]) → List[List[float]][source]#
Call out to Aleph Alpha’s asymmetric Document endpoint.
Parameters
texts – The list of texts to embed.
Returns | https://python.langchain.com/en/latest/reference/modules/embeddings.html |
cc47f48085d0-1 | Parameters
texts – The list of texts to embed.
Returns
List of embeddings, one for each text.
embed_query(text: str) → List[float][source]#
Call out to Aleph Alpha’s asymmetric, query embedding endpoint
:param text: The text to embed.
Returns
Embeddings for the text.
pydantic model langchain.embeddings.AlephAlphaSymmetricSemanticEmbedding[source]#
The symmetric version of the Aleph Alpha’s semantic embeddings.
The main difference is that here, both the documents and
queries are embedded with a SemanticRepresentation.Symmetric
.. rubric:: Example
embed_documents(texts: List[str]) → List[List[float]][source]#
Call out to Aleph Alpha’s Document endpoint.
Parameters
texts – The list of texts to embed.
Returns
List of embeddings, one for each text.
embed_query(text: str) → List[float][source]#
Call out to Aleph Alpha’s asymmetric, query embedding endpoint
:param text: The text to embed.
Returns
Embeddings for the text.
pydantic model langchain.embeddings.CohereEmbeddings[source]#
Wrapper around Cohere embedding models.
To use, you should have the cohere python package installed, and the
environment variable COHERE_API_KEY set with your API key or pass it
as a named parameter to the constructor.
Example
from langchain.embeddings import CohereEmbeddings
cohere = CohereEmbeddings(model="medium", cohere_api_key="my-api-key")
field model: str = 'large'#
Model name to use.
field truncate: Optional[str] = None#
Truncate embeddings that are too long from start or end (“NONE”|”START”|”END”)
embed_documents(texts: List[str]) → List[List[float]][source]# | https://python.langchain.com/en/latest/reference/modules/embeddings.html |