The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
docs: model parameter mandatory for cohere embedding and rerank (#23349)
Anirudh314159265357677ceea6015
diff --git a/docs/docs/how_to/embed_text.mdx b/docs/docs/how_to/embed_text.mdxindex ed75a36a62..0cf48c24ec 100644--- a/docs/docs/how_to/embed_text.mdx+++ b/docs/docs/how_to/embed_text.mdx@@ -67,15 +67,16 @@ If you'd prefer not to set an environment variable you can pass the key in direc```pythonfrom langchain_cohere import CohereEmbeddings-embeddings_model = CohereEmbeddings(cohere_api_key="...")+embeddings_model = CohereEmbeddings(cohere_api_key="...", model='embed-english-v3.0')```-Otherwise you can initialize without any params:+Otherwise you can initialize simply as shown below:```pythonfrom langchain_cohere import CohereEmbeddings-embeddings_model = CohereEmbeddings()+embeddings_model = CohereEmbeddings(model='embed-english-v3.0')```+Do note that it is mandatory to pass the model parameter while initializing the CohereEmbeddings class.</TabItem><TabItem value="huggingface" label="Hugging Face">diff --git a/docs/docs/integrations/retrievers/cohere-reranker.ipynb b/docs/docs/integrations/retrievers/cohere-reranker.ipynbindex 623869d02c..4054aad8e7 100644--- a/docs/docs/integrations/retrievers/cohere-reranker.ipynb+++ b/docs/docs/integrations/retrievers/cohere-reranker.ipynb@@ -309,9 +309,9 @@"documents = TextLoader(\"../../how_to/state_of_the_union.txt\").load()\n","text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)\n","texts = text_splitter.split_documents(documents)\n",- "retriever = FAISS.from_documents(texts, CohereEmbeddings()).as_retriever(\n",- " search_kwargs={\"k\": 20}\n",- ")\n",+ "retriever = FAISS.from_documents(\n",+ " texts, CohereEmbeddings(model=\"embed-english-v3.0\")\n",+ ").as_retriever(search_kwargs={\"k\": 20})\n","\n","query = \"What did the president say about Ketanji Brown Jackson\"\n","docs = retriever.invoke(query)\n",@@ -324,7 +324,8 @@"metadata": {},"source": ["## Doing reranking with CohereRerank\n",- "Now let's wrap our base retriever with a `ContextualCompressionRetriever`. We'll add an `CohereRerank`, uses the Cohere rerank endpoint to rerank the returned results."+ "Now let's wrap our base retriever with a `ContextualCompressionRetriever`. We'll add an `CohereRerank`, uses the Cohere rerank endpoint to rerank the returned results.\n",+ "Do note that it is mandatory to specify the model name in CohereRerank!"]},{@@ -339,7 +340,7 @@"from langchain_community.llms import Cohere\n","\n","llm = Cohere(temperature=0)\n",- "compressor = CohereRerank()\n",+ "compressor = CohereRerank(model=\"rerank-english-v3.0\")\n","compression_retriever = ContextualCompressionRetriever(\n"," base_compressor=compressor, base_retriever=retriever\n",")\n",diff --git a/docs/docs/integrations/text_embedding/cohere.ipynb b/docs/docs/integrations/text_embedding/cohere.ipynbindex d8273163ca..d13cd450b0 100644--- a/docs/docs/integrations/text_embedding/cohere.ipynb+++ b/docs/docs/integrations/text_embedding/cohere.ipynb@@ -40,7 +40,9 @@"metadata": {},"outputs": [],"source": [- "embeddings = CohereEmbeddings(model=\"embed-english-light-v3.0\")"+ "embeddings = CohereEmbeddings(\n",+ " model=\"embed-english-light-v3.0\"\n",+ ") # It is mandatory to pass a model parameter to initialize the CohereEmbeddings object"]},{diff --git a/docs/docs/integrations/vectorstores/pgvector.ipynb b/docs/docs/integrations/vectorstores/pgvector.ipynbindex 85bbc3bcf4..0a83ccb219 100644--- a/docs/docs/integrations/vectorstores/pgvector.ipynb+++ b/docs/docs/integrations/vectorstores/pgvector.ipynb@@ -78,7 +78,7 @@"# See docker command above to launch a postgres instance with pgvector enabled.\n","connection = \"postgresql+psycopg://langchain:langchain@localhost:6024/langchain\" # Uses psycopg3!\n","collection_name = \"my_docs\"\n",- "embeddings = CohereEmbeddings()\n",+ "embeddings = CohereEmbeddings(model=\"embed-english-v3.0\")\n","\n","vectorstore = PGVector(\n"," embeddings=embeddings,\n",diff --git a/templates/cohere-librarian/cohere_librarian/blurb_matcher.py b/templates/cohere-librarian/cohere_librarian/blurb_matcher.pyindex c029935aaf..50e63827a0 100644--- a/templates/cohere-librarian/cohere_librarian/blurb_matcher.py+++ b/templates/cohere-librarian/cohere_librarian/blurb_matcher.py@@ -23,7 +23,7 @@ parsed_data = []parsed_data[1]-embeddings = CohereEmbeddings()+embeddings = CohereEmbeddings(model="embed-english-v3.0")docsearch = Chroma.from_texts([x["title"] for x in parsed_data], embeddings, metadatas=parsed_data