github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-11 05:45:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

fleet_context docs update (#13221)

Browse Source 
- **Description:** Changed the fleet_context documentation to use
`context.download_embeddings()` from the latest release from our
package. More details here:
https://github.com/fleet-ai/context/tree/main#api
  - **Issue:** n/a
  - **Dependencies:** n/a
  - **Tag maintainer:** @baskaryan 
  - **Twitter handle:** @andrewthezhou
This commit is contained in:
Andrew Zhou 2023-11-10 17:53:57 -05:00 committed by GitHub
parent 8fdf15c023
commit 1a1a1a883f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 10 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
docs/docs/integrations/retrievers/fleet_context.ipynb
View File

@ -19,7 +19,7 @@
"metadata": {},
"outputs": [],
"source": [
"!pip install langchain openai pandas faiss-cpu # faiss-gpu for CUDA supported GPU"
"!pip install langchain fleet-context openai pandas faiss-cpu # faiss-gpu for CUDA supported GPU"
]
},
{
@ -43,13 +43,12 @@
"\n",
"\n",
"def load_fleet_retriever(\n",
" url: str,\n",
" df: pd.DataFrame,\n",
" *,\n",
" vectorstore_cls: Type[VectorStore] = FAISS,\n",
" docstore: Optional[BaseStore] = None,\n",
" **kwargs: Any,\n",
"):\n",
" df = pd.read_parquet(url)\n",
" vectorstore = _populate_vectorstore(df, vectorstore_cls)\n",
" if docstore is None:\n",
" return vectorstore.as_retriever(**kwargs)\n",
@ -106,7 +105,10 @@
"source": [
"## Retriever chunks\n",
"\n",
"As part of their embedding process, the Fleet AI team first chunked long documents before embedding them. This means the vectors correspond to sections of pages in the LangChain docs, not entire pages. By default, when we spin up a retriever from these embeddings, we'll be retrieving these embedded chunks:"
"As part of their embedding process, the Fleet AI team first chunked long documents before embedding them. This means the vectors correspond to sections of pages in the LangChain docs, not entire pages. By default, when we spin up a retriever from these embeddings, we'll be retrieving these embedded chunks.",
"\n",
"\n",
"We will be using Fleet Context's `download_embeddings()` to grab Langchain's documentation embeddings. You can view all supported libraries' documentation at https://fleet.so/context."
]
},
{
@ -116,9 +118,10 @@
"metadata": {},
"outputs": [],
"source": [
"vecstore_retriever = load_fleet_retriever(\n",
" \"https://www.dropbox.com/scl/fi/4rescpkrg9970s3huz47l/libraries_langchain_release.parquet?rlkey=283knw4wamezfwiidgpgptkep&dl=1\",\n",
")"
"from context import download_embeddings\n",
"\n",
"df = download_embeddings(\"langchain\")\n",
"vecstore_retriever = load_fleet_retriever(df)"
]
},
{