neuml/txtai
1
0
Fork 0
mirror of https://github.com/neuml/txtai.git synced 2026-10-12 02:19:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update dependency version

Browse Source
This commit is contained in:
davidmezzetti
2025-04-07 18:43:05 -04:00
parent 642ef2307a
commit a3f0896961
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/73_Chunking_your_data_for_RAG.ipynb
+1 -1
View File
@@ -40,7 +40,7 @@
"\n",
"Let's dive right in and keep this example simple. The next section creates a [Textractor pipeline](https://neuml.github.io/txtai/pipeline/data/textractor/) and an [Embeddings database](https://neuml.github.io/txtai/embeddings/).\n",
"\n",
"The `Textractor` extracts chunks of text from files and the `Embeddings` takes those chunks and builds an index/database. We'll use a [late chunker](https://docs.chonkie.ai/chunkers/late-chunker) backed by [Chonkie](https://github.com/chonkie-ai/chonkie).\n",
"The `Textractor` extracts chunks of text from files and the `Embeddings` takes those chunks and builds an index/database. We'll use a [late chunker](https://docs.chonkie.ai/chunkers/late-chunker) backed by [Chonkie](https://github.com/chonkie-inc/chonkie).\n",
"\n",
"Then, we'll build an indexing workflow that streams chunks from two files."
]
setup.py
+1 -1
View File
@@ -63,7 +63,7 @@ extras["pipeline-audio"] = [
"webrtcvad-wheels>=2.0.14",
]
extras["pipeline-data"] = ["beautifulsoup4>=4.9.3", "chonkie>=0.4.1", "docling>=2.8.2", "nltk>=3.5", "pandas>=1.1.0", "tika>=1.24"]
extras["pipeline-data"] = ["beautifulsoup4>=4.9.3", "chonkie>=1.0.2", "docling>=2.8.2", "nltk>=3.5", "pandas>=1.1.0", "tika>=1.24"]
extras["pipeline-image"] = ["imagehash>=4.2.1", "pillow>=7.1.2", "timm>=0.4.12"]