github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-04-27 11:41:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs,langchain-community: Fix typos in docs and code (#30541)

Browse Source 
Fix typos
This commit is contained in:
omahs 2025-03-28 20:21:16 +01:00 committed by GitHub
parent 47d50f49d9
commit 6f8735592b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
21 changed files with 54 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
cookbook/img-to_img-search_CLIP_ChromaDB.ipynb
View File

@ -358,7 +358,7 @@
"id": "6e5cd014-db86-4d6b-8399-25cae3da5570",
"metadata": {},
"source": [
"## Helper function to plot retrived similar images"
"## Helper function to plot retrieved similar images"
]
},
{

2
docs/docs/how_to/qa_citations.ipynb
View File

@ -127,7 +127,7 @@
"id": "c89e2045-9244-43e6-bf3f-59af22658529",
"metadata": {},
"source": [
"Now that we've got a [model](/docs/concepts/chat_models/), [retriver](/docs/concepts/retrievers/) and [prompt](/docs/concepts/prompt_templates/), let's chain them all together. Following the how-to guide on [adding citations](/docs/how_to/qa_citations) to a RAG application, we'll make it so our chain returns both the answer and the retrieved Documents. This uses the same [LangGraph](/docs/concepts/architecture/#langgraph) implementation as in the [RAG Tutorial](/docs/tutorials/rag)."
"Now that we've got a [model](/docs/concepts/chat_models/), [retriever](/docs/concepts/retrievers/) and [prompt](/docs/concepts/prompt_templates/), let's chain them all together. Following the how-to guide on [adding citations](/docs/how_to/qa_citations) to a RAG application, we'll make it so our chain returns both the answer and the retrieved Documents. This uses the same [LangGraph](/docs/concepts/architecture/#langgraph) implementation as in the [RAG Tutorial](/docs/tutorials/rag)."
]
},
{

2
docs/docs/how_to/query_multiple_queries.ipynb
View File

@ -270,7 +270,7 @@
"source": [
"## Retrieval with query analysis\n",
"\n",
"So how would we include this in a chain? One thing that will make this a lot easier is if we call our retriever asyncronously - this will let us loop over the queries and not get blocked on the response time."
"So how would we include this in a chain? One thing that will make this a lot easier is if we call our retriever asynchronously - this will let us loop over the queries and not get blocked on the response time."
]
},
{

2
docs/docs/how_to/summarize_map_reduce.ipynb
View File

@ -24,7 +24,7 @@
"\n",
"Note that the map step is typically parallelized over the input documents. This strategy is especially effective when understanding of a sub-document does not rely on preceeding context. For example, when summarizing a corpus of many, shorter documents.\n",
"\n",
"[LangGraph](https://langchain-ai.github.io/langgraph/), built on top of `langchain-core`, suports [map-reduce](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/) workflows and is well-suited to this problem:\n",
"[LangGraph](https://langchain-ai.github.io/langgraph/), built on top of `langchain-core`, supports [map-reduce](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/) workflows and is well-suited to this problem:\n",
"\n",
"- LangGraph allows for individual steps (such as successive summarizations) to be streamed, allowing for greater control of execution;\n",
"- LangGraph's [checkpointing](https://langchain-ai.github.io/langgraph/how-tos/persistence/) supports error recovery, extending with human-in-the-loop workflows, and easier incorporation into conversational applications.\n",

2
docs/docs/integrations/llms/bittensor.ipynb
View File

@ -48,7 +48,7 @@
"print(f\"Response provided by LLM with system prompt set is : {sys_resp}\")\n",
"\n",
"# The top_responses parameter can give multiple responses based on its parameter value\n",
"# This below code retrive top 10 miner's response all the response are in format of json\n",
"# This below code retrieve top 10 miner's response all the response are in format of json\n",
"\n",
"# Json response structure is\n",
"\"\"\" {\n",

2
docs/docs/integrations/retrievers/zotero.ipynb
View File

@ -198,7 +198,7 @@
"\n",
" Args:\n",
" query: str: The search query to be used. Try to keep this specific and short, e.g. a specific topic or author name\n",
" itemType: Optional. Type of item to search for (e.g. \"book\" or \"journalArticle\"). Multiple types can be passed as a string seperated by \"||\", e.g. \"book || journalArticle\". Defaults to all types.\n",
" itemType: Optional. Type of item to search for (e.g. \"book\" or \"journalArticle\"). Multiple types can be passed as a string separated by \"||\", e.g. \"book || journalArticle\". Defaults to all types.\n",
" tag: Optional. For searching over tags attached to library items. If documents tagged with multiple tags are to be retrieved, pass them as a list. If documents with any of the tags are to be retrieved, pass them as a string separated by \"||\", e.g. \"tag1 || tag2\"\n",
" qmode: Search mode to use. Changes what the query searches over. \"everything\" includes full-text content. \"titleCreatorYear\" to search over title, authors and year. Defaults to \"everything\".\n",
" since: Return only objects modified after the specified library version. Defaults to return everything.\n",

2
docs/docs/integrations/tools/cassandra_database.ipynb
View File

@ -70,7 +70,7 @@
"Gathers all schema information for the connected database or a specific schema. Critical for the agent when determining actions. \n",
"\n",
"### `cassandra_db_select_table_data`\n",
"Selects data from a specific keyspace and table. The agent can pass paramaters for a predicate and limits on the number of returned records. \n",
"Selects data from a specific keyspace and table. The agent can pass parameters for a predicate and limits on the number of returned records. \n",
"\n",
"### `cassandra_db_query`\n",
"Expiriemental alternative to `cassandra_db_select_table_data` which takes a query string completely formed by the agent instead of parameters. *Warning*: This can lead to unusual queries that may not be as performant(or even work). This may be removed in future releases. If it does something cool, we want to know about that too. You never know!"

2
docs/docs/integrations/vectorstores/baiducloud_vector_search.ipynb
View File

@ -123,7 +123,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Finally, Query and retrive data"
"Finally, Query and retrieve data"
]
},
{

2
docs/docs/integrations/vectorstores/ecloud_vector_search.ipynb
View File

@ -123,7 +123,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Finally, Query and retrive data"
"Finally, Query and retrieve data"
]
},
{

2
docs/docs/integrations/vectorstores/vearch.ipynb
View File

@ -436,7 +436,7 @@
}
],
"source": [
"##delete and get function need to maintian docids\n",
"##delete and get function need to maintain docids\n",
"##your docid\n",
"\n",
"res_d = vearch_standalone.delete(\n",

2
docs/docs/versions/migrating_chains/map_reduce_chain.ipynb
View File

@ -19,7 +19,7 @@
"\n",
"In the reduce step, `MapReduceDocumentsChain` supports a recursive \"collapsing\" of the summaries: the inputs would be partitioned based on a token limit, and summaries would be generated of the partitions. This step would be repeated until the total length of the summaries was within a desired limit, allowing for the summarization of arbitrary-length text. This is particularly useful for models with smaller context windows.\n",
"\n",
"LangGraph suports [map-reduce](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/) workflows, and confers a number of advantages for this problem:\n",
"LangGraph supports [map-reduce](https://langchain-ai.github.io/langgraph/how-tos/map-reduce/) workflows, and confers a number of advantages for this problem:\n",
"\n",
"- LangGraph allows for individual steps (such as successive summarizations) to be streamed, allowing for greater control of execution;\n",
"- LangGraph's [checkpointing](https://langchain-ai.github.io/langgraph/how-tos/persistence/) supports error recovery, extending with human-in-the-loop workflows, and easier incorporation into conversational applications.\n",

2
libs/community/langchain_community/chat_models/premai.py
View File

@ -244,7 +244,7 @@ def _messages_to_prompt_dict(
else:
raise ChatPremAPIError("No such role explicitly exists")
# do a seperate search for tool calls
# do a separate search for tool calls
tool_prompt = ""
for input_msg in input_messages:
if isinstance(input_msg, ToolMessage):

2
libs/community/langchain_community/vectorstores/documentdb.py
View File

@ -327,7 +327,7 @@ class DocumentDBVectorSearch(VectorStore):
Returns:
A list of documents closest to the query vector
"""
# $match can't be null, so intializes to {} when None to avoid
# $match can't be null, so initializes to {} when None to avoid
# "the match filter must be an expression in an object"
if not filter:
filter = {}

2
libs/community/langchain_community/vectorstores/faiss.py
View File

@ -1352,7 +1352,7 @@ class FAISS(VectorStore):
satisfies the filter conditions, otherwise False.
Raises:
ValueError: If the filter is invalid or contains unsuported operators.
ValueError: If the filter is invalid or contains unsupported operators.
"""
if callable(filter):
return filter

8
libs/community/langchain_community/vectorstores/falkordb_vector.py
View File

@ -690,7 +690,7 @@ class FalkorDBVector(VectorStore):
"}) has already been created"
)
else:
raise ValueError(f"Error occured: {e}")
raise ValueError(f"Error occurred: {e}")
def create_new_index_on_relationship(
self,
@ -739,7 +739,7 @@ class FalkorDBVector(VectorStore):
"}] has already been created"
)
else:
raise ValueError(f"Error occured: {e}")
raise ValueError(f"Error occurred: {e}")
def create_new_keyword_index(self, text_node_properties: List[str] = []) -> None:
"""
@ -1152,7 +1152,7 @@ class FalkorDBVector(VectorStore):
Args:
embedding: The `Embeddings` model you would like to use
database: The name of the existing graph/database you
would like to intialize
would like to initialize
node_label: The label of the node you want to initialize.
embedding_node_property: The name of the property you
want your embeddings to be stored in.
@ -1633,7 +1633,7 @@ class FalkorDBVector(VectorStore):
for result in sorted_results
]
except Exception as e:
raise ValueError(f"An error occured: {e}")
raise ValueError(f"An error occurred: {e}")
return docs

2
libs/community/tests/integration_tests/vectorstores/test_azure_cosmos_db.py
View File

@ -82,7 +82,7 @@ class TestAzureCosmosDBVectorSearch:
if not os.getenv("AZURE_OPENAI_API_VERSION"):
raise ValueError("AZURE_OPENAI_API_VERSION environment variable is not set")
# insure the test collection is empty
# ensure the test collection is empty
collection = prepare_collection()
assert collection.count_documents({}) == 0 # type: ignore[index]

2
libs/community/tests/integration_tests/vectorstores/test_documentdb.py
View File

@ -69,7 +69,7 @@ class TestDocumentDBVectorSearch:
if not os.getenv("OPENAI_API_KEY"):
raise ValueError("OPENAI_API_KEY environment variable is not set")
# insure the test collection is empty
# ensure the test collection is empty
collection = prepare_collection()
assert collection.count_documents({}) == 0 # type: ignore[index]

62
libs/community/tests/integration_tests/vectorstores/test_hanavector.py
View File

@ -170,7 +170,7 @@ def test_hanavector_table_with_missing_columns() -> None:
cur.close()
# Check if table is created
exception_occured = False
exception_occurred = False
try:
HanaDB(
connection=test_setup.conn,
@ -178,10 +178,10 @@ def test_hanavector_table_with_missing_columns() -> None:
distance_strategy=DistanceStrategy.COSINE,
table_name=table_name,
)
exception_occured = False
exception_occurred = False
except AttributeError:
exception_occured = True
assert exception_occured
exception_occurred = True
assert exception_occurred
@pytest.mark.skipif(not hanadb_installed, reason="hanadb not installed")
@ -243,7 +243,7 @@ def test_hanavector_table_with_wrong_typed_columns() -> None:
cur.close()
# Check if table is created
exception_occured = False
exception_occurred = False
try:
HanaDB(
connection=test_setup.conn,
@ -251,11 +251,11 @@ def test_hanavector_table_with_wrong_typed_columns() -> None:
distance_strategy=DistanceStrategy.COSINE,
table_name=table_name,
)
exception_occured = False
exception_occurred = False
except AttributeError as err:
print(err) # noqa: T201
exception_occured = True
assert exception_occured
exception_occurred = True
assert exception_occurred
@pytest.mark.skipif(not hanadb_installed, reason="hanadb not installed")
@ -521,12 +521,12 @@ def test_hanavector_similarity_search_with_metadata_filter_invalid_type(
table_name=table_name,
)
exception_occured = False
exception_occurred = False
try:
vectorDB.similarity_search(texts[0], 3, filter={"wrong_type": 0.1})
except ValueError:
exception_occured = True
assert exception_occured
exception_occurred = True
assert exception_occurred
@pytest.mark.skipif(not hanadb_installed, reason="hanadb not installed")
@ -727,20 +727,20 @@ def test_hanavector_delete_called_wrong(
)
# Delete without filter parameter
exception_occured = False
exception_occurred = False
try:
vectorDB.delete()
except ValueError:
exception_occured = True
assert exception_occured
exception_occurred = True
assert exception_occurred
# Delete with ids parameter
exception_occured = False
exception_occurred = False
try:
vectorDB.delete(ids=["id1", "id"], filter={"start": 100, "end": 200})
except ValueError:
exception_occured = True
assert exception_occured
exception_occurred = True
assert exception_occurred
@pytest.mark.skipif(not hanadb_installed, reason="hanadb not installed")
@ -884,7 +884,7 @@ def test_invalid_metadata_keys(texts: List[str], metadatas: List[dict]) -> None:
invalid_metadatas = [
{"sta rt": 0, "end": 100, "quality": "good", "ready": True},
]
exception_occured = False
exception_occurred = False
try:
HanaDB.from_texts(
connection=test_setup.conn,
@ -894,13 +894,13 @@ def test_invalid_metadata_keys(texts: List[str], metadatas: List[dict]) -> None:
table_name=table_name,
)
except ValueError:
exception_occured = True
assert exception_occured
exception_occurred = True
assert exception_occurred
invalid_metadatas = [
{"sta/nrt": 0, "end": 100, "quality": "good", "ready": True},
]
exception_occured = False
exception_occurred = False
try:
HanaDB.from_texts(
connection=test_setup.conn,
@ -910,8 +910,8 @@ def test_invalid_metadata_keys(texts: List[str], metadatas: List[dict]) -> None:
table_name=table_name,
)
except ValueError:
exception_occured = True
assert exception_occured
exception_occurred = True
assert exception_occurred
@pytest.mark.skipif(not hanadb_installed, reason="hanadb not installed")
@ -1361,7 +1361,7 @@ def test_preexisting_specific_columns_for_metadata_wrong_type_or_non_existing(
cur.close()
# Check if table is created
exception_occured = False
exception_occurred = False
try:
HanaDB.from_texts(
connection=test_setup.conn,
@ -1371,12 +1371,12 @@ def test_preexisting_specific_columns_for_metadata_wrong_type_or_non_existing(
table_name=table_name,
specific_metadata_columns=["quality"],
)
exception_occured = False
exception_occurred = False
except dbapi.Error: # Nothing we should do here, hdbcli will throw an error
exception_occured = True
assert exception_occured # Check if table is created
exception_occurred = True
assert exception_occurred # Check if table is created
exception_occured = False
exception_occurred = False
try:
HanaDB.from_texts(
connection=test_setup.conn,
@ -1386,10 +1386,10 @@ def test_preexisting_specific_columns_for_metadata_wrong_type_or_non_existing(
table_name=table_name,
specific_metadata_columns=["NonExistingColumn"],
)
exception_occured = False
exception_occurred = False
except AttributeError: # Nothing we should do here, hdbcli will throw an error
exception_occured = True
assert exception_occured
exception_occurred = True
assert exception_occurred
@pytest.mark.skipif(not hanadb_installed, reason="hanadb not installed")

2
libs/community/tests/integration_tests/vectorstores/test_mongodb_atlas.py
View File

@ -33,7 +33,7 @@ def collection() -> Any:
class TestMongoDBAtlasVectorSearch:
@classmethod
def setup_class(cls) -> None:
# insure the test collection is empty
# ensure the test collection is empty
collection = get_collection()
assert collection.count_documents({}) == 0 # type: ignore[index]

2
libs/community/tests/integration_tests/vectorstores/test_pinecone.py
View File

@ -59,7 +59,7 @@ class TestPinecone:
else:
pinecone.create_index(name=index_name, dimension=dimension)
# insure the index is empty
# ensure the index is empty
index_stats = cls.index.describe_index_stats()
assert index_stats["dimension"] == dimension
if index_stats["namespaces"].get(namespace_name) is not None:

2
libs/partners/openai/tests/unit_tests/embeddings/test_azure_embeddings.py
View File

@ -15,7 +15,7 @@ def test_initialize_azure_openai() -> None:
assert embeddings.model == "text-embedding-large"
def test_intialize_azure_openai_with_base_set() -> None:
def test_initialize_azure_openai_with_base_set() -> None:
with mock.patch.dict(os.environ, {"OPENAI_API_BASE": "https://api.openai.com"}):
embeddings = AzureOpenAIEmbeddings( # type: ignore[call-arg, call-arg]
model="text-embedding-large",