ragbandit-core 0.1.1__py3-none-any.whl → 0.1.2__py3-none-any.whl

ragbandit/documents/chunkers/semantic_chunker.py

@@ -99,9 +99,9 @@ class SemanticChunker(BaseChunker):
                         ]
                         idx = full_text.find(current_break_lead)
 
-                if idx == -1:
-                    # If we still can't find the snippet after
-                    # trying shorter versions,
+                if idx == -1 or idx == 0:
+                    # If we can't find the snippet, or if the break is at
+                    # the very start (idx == 0 would create an empty chunk),
                     # fallback: chunk everything as is
                     meta = ChunkMetadata(page_index=i, images=[], extra={})
                     chunks.append(Chunk(text=full_text, metadata=meta))

{ragbandit_core-0.1.1.dist-info → ragbandit_core-0.1.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ragbandit-core
-Version: 0.1.1
+Version: 0.1.2
 Summary: Core utilities for document processing, RAG configuration, querying, and evaluation.
 Author-email: Martim Chaves <martim@ragbandit.com>
 License: MIT

{ragbandit_core-0.1.1.dist-info → ragbandit_core-0.1.2.dist-info}/RECORD

@@ -8,7 +8,7 @@ ragbandit/documents/document_pipeline.py,sha256=bDmOjhj8mIbMii3ZTLHA5blzPvdMmD_w
 ragbandit/documents/chunkers/__init__.py,sha256=U2ptxUtW-e_OCl50kjg-YmKD2e1eGI6iPAWl8hG2W0s,464
 ragbandit/documents/chunkers/base_chunker.py,sha256=9sCEqn-uVesvYOh2aNbjoN9-mkkAQxml8-nuonr5zUk,6616
 ragbandit/documents/chunkers/fixed_size_chunker.py,sha256=--OQ5XVhATw4v_MEmfTJPkfUQ2fHXCJyYpWktWVi9JY,5764
-ragbandit/documents/chunkers/semantic_chunker.py,sha256=67I2TjytMSB_LWloGWhesOB7Hu4RlYBUsr9T8A9SD2I,7188
+ragbandit/documents/chunkers/semantic_chunker.py,sha256=Qf-dQNCUk84y69Z_MxhG_vO5GsejojdHWnQX9uUCi_E,7241
 ragbandit/documents/embedders/__init__.py,sha256=6do7BGP8rHCLvIoPIwcK5W751jl8spEfq2smgkoTK3o,418
 ragbandit/documents/embedders/base_embedder.py,sha256=Bdbmhvi82JxRCBtaY6ZFIbmmPkHriTqtZvvRs6k3dfg,2287
 ragbandit/documents/embedders/mistral_embedder.py,sha256=T0FPILc7PKIgWxV_lWQbqyP5_LElkuuGtDvn4-Ec6d8,4242
@@ -31,8 +31,8 @@ ragbandit/utils/in_memory_log_handler.py,sha256=vMtCG-Wk9OwiCo2087nQovSIOQCu5ZWX
 ragbandit/utils/llm_utils.py,sha256=7motkdeez9D_eEBemY6Mw_tZZCCyvt886GEYHv9ddvs,7079
 ragbandit/utils/mistral_client.py,sha256=VkqFgquyjCmUllBjrHKqQnnmvU3yF0frvCSVIkHH-jQ,2195
 ragbandit/utils/token_usage_tracker.py,sha256=CMAuJolcdJ258CVMkpNVhZAnQIGC-jTnxYkOr2jvp0M,7196
-ragbandit_core-0.1.1.dist-info/licenses/LICENSE.md,sha256=rZBctov8cSToljMmrdApur6WqyMIrX0KjkMKDpqx9w8,1070
-ragbandit_core-0.1.1.dist-info/METADATA,sha256=FsGiCB_o8_vMQohVWsGN_o3gHzdM1usLA9Xw5zEi7bc,3924
-ragbandit_core-0.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ragbandit_core-0.1.1.dist-info/top_level.txt,sha256=UDjwZ4afIob8DIsuV6D08lU5bHCeN00grjXpzgDhsQ8,10
-ragbandit_core-0.1.1.dist-info/RECORD,,
+ragbandit_core-0.1.2.dist-info/licenses/LICENSE.md,sha256=rZBctov8cSToljMmrdApur6WqyMIrX0KjkMKDpqx9w8,1070
+ragbandit_core-0.1.2.dist-info/METADATA,sha256=oX0mi24XkPF58dd2xOIY-0IkNFmYqhl1g1Qw7rXaok0,3924
+ragbandit_core-0.1.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ragbandit_core-0.1.2.dist-info/top_level.txt,sha256=UDjwZ4afIob8DIsuV6D08lU5bHCeN00grjXpzgDhsQ8,10
+ragbandit_core-0.1.2.dist-info/RECORD,,