langroid 0.1.160__py3-none-any.whl → 0.1.162__py3-none-any.whl

langroid/agent/chat_agent.py

@@ -50,7 +50,7 @@ class ChatAgentConfig(AgentConfig):
         depending on config settings and availability of fn-calling.
         """
         if self.use_functions_api and not fn_available:
-            logger.warning(
+            logger.debug(
                 """
                 You have enabled `use_functions_api` but the LLM does not support it.
                 So we will enable `use_tools` instead, so we can use 
@@ -63,7 +63,7 @@ class ChatAgentConfig(AgentConfig):
         if not self.use_functions_api or not self.use_tools:
             return
         if self.use_functions_api and self.use_tools:
-            logger.warning(
+            logger.debug(
                 """
                 You have enabled both `use_tools` and `use_functions_api`.
                 Turning off `use_tools`, since the LLM supports function-calling.

langroid/agent/special/lance_doc_chat_agent.py

@@ -84,6 +84,12 @@ class LanceDocChatAgent(DocChatAgent):
             logger.error(f"Error setting up documents: {e}")
             # say DONE with err msg so it goes back to LanceFilterAgent
             return f"{DONE} Possible Filter Error:\n {e}"
+        if plan.query is None or plan.query.strip() == "":
+            # Empty query, say DONE with a message to parent's LLM to try again
+            return """DONE
+                   Rephrased query in QueryPlan cannot be empty.
+                   Please try again.
+                   """
         # update the filter so it is used in the DocChatAgent
         self.config.filter = plan.filter or None
         if plan.dataframe_calc:

langroid/agent/special/sql/sql_chat_agent.py

@@ -227,8 +227,10 @@ class SQLChatAgent(ChatAgent):
         if isinstance(msg, ChatDocument) and msg.function_call is not None:
             sender_name = msg.function_call.name
 
+        content = results.content if isinstance(results, ChatDocument) else results
+
         return ChatDocument(
-            content=results,
+            content=content,
             metadata=ChatDocMetaData(
                 source=Entity.AGENT,
                 sender=Entity.AGENT,

langroid/parsing/utils.py

@@ -101,14 +101,33 @@ def split_paragraphs(text: str) -> List[str]:
     return [para.strip() for para in paras if para.strip()]
 
 
-def number_segments(s: str, len: int = 1) -> str:
+def split_newlines(text: str) -> List[str]:
+    """
+    Split the input text into lines using "\n" as the delimiter.
+
+    Args:
+        text (str): The input text.
+
+    Returns:
+        list: A list of lines.
+    """
+    lines = re.split(r"\n", text)
+    return [line.strip() for line in lines if line.strip()]
+
+
+def number_segments(s: str, granularity: int = 1) -> str:
     """
     Number the segments in a given text, preserving paragraph structure.
-    A segment is a sequence of `len` consecutive sentences.
+    A segment is a sequence of `len` consecutive "sentences", where a "sentence"
+    is either a normal sentence, or if there isn't enough punctuation to properly
+    identify sentences, then we use a pseudo-sentence via heuristics (split by newline
+    or failing that, just split every 40 words). The goal here is simply to number
+    segments at a reasonable granularity so the LLM can identify relevant segments,
+    in the RelevanceExtractorAgent.
 
     Args:
         s (str): The input text.
-        len (int): The number of sentences in a segment.
+        granularity (int): The number of sentences in a segment.
             If this is -1, then the entire text is treated as a single segment,
             and is numbered as <#1#>.
 
@@ -119,7 +138,7 @@ def number_segments(s: str, len: int = 1) -> str:
         >>> number_segments("Hello world! How are you? Have a good day.")
         '<#1#> Hello world! <#2#> How are you? <#3#> Have a good day.'
     """
-    if len < 0:
+    if granularity < 0:
         return "<#1#> " + s
     numbered_text = []
     count = 0
@@ -127,9 +146,34 @@ def number_segments(s: str, len: int = 1) -> str:
     paragraphs = split_paragraphs(s)
     for paragraph in paragraphs:
         sentences = nltk.sent_tokenize(paragraph)
+        # Some docs are problematic (e.g. resumes) and have no (or too few) periods,
+        # so we can't split usefully into sentences.
+        # We try a series of heuristics to split into sentences,
+        # until the avg num words per sentence is less than 40.
+        avg_words_per_sentence = sum(
+            len(nltk.word_tokenize(sentence)) for sentence in sentences
+        ) / len(sentences)
+        if avg_words_per_sentence > 40:
+            sentences = split_newlines(paragraph)
+        avg_words_per_sentence = sum(
+            len(nltk.word_tokenize(sentence)) for sentence in sentences
+        ) / len(sentences)
+        if avg_words_per_sentence > 40:
+            # Still too long, just split on every 40 words
+            sentences = []
+            for sentence in nltk.sent_tokenize(paragraph):
+                words = nltk.word_tokenize(sentence)
+                for i in range(0, len(words), 40):
+                    # if there are less than 20 words left after this,
+                    # just add them to the last sentence and break
+                    if len(words) - i < 20:
+                        sentences.append(" ".join(words[i:]))
+                        break
+                    else:
+                        sentences.append(" ".join(words[i : i + 40]))
         for i, sentence in enumerate(sentences):
-            num = count // len + 1
-            number_prefix = f"<#{num}#>" if count % len == 0 else ""
+            num = count // granularity + 1
+            number_prefix = f"<#{num}#>" if count % granularity == 0 else ""
             sentence = f"{number_prefix} {sentence}"
             count += 1
             sentences[i] = sentence
@@ -140,7 +184,7 @@ def number_segments(s: str, len: int = 1) -> str:
 
 
 def number_sentences(s: str) -> str:
-    return number_segments(s, len=1)
+    return number_segments(s, granularity=1)
 
 
 def parse_number_range_list(specs: str) -> List[int]:

{langroid-0.1.160.dist-info → langroid-0.1.162.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.1.160
+Version: 0.1.162
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani

{langroid-0.1.160.dist-info → langroid-0.1.162.dist-info}/RECORD

@@ -2,14 +2,14 @@ langroid/__init__.py,sha256=mlQxyJTPRJjTon0D5MlzpMHQ0jwdzSIEpiB0A6mZR7A,477
 langroid/agent/__init__.py,sha256=ZqDw3Ktw7XGDl6mC8DN61F71V4ckf0rBoEOydH9l6C4,428
 langroid/agent/base.py,sha256=Cs-TQV_a5Vxdt0A3p1rvW1XGDN7g2zVqtyBhGco0_EE,33156
 langroid/agent/batch.py,sha256=Cg7Qv1yGi_M9rMl38_4-hjXPsoLlZrOSXDhbOFqUcKY,5593
-langroid/agent/chat_agent.py,sha256=TaSxTnA6jA1QnbClkyPxuFZXbHDS2hg_bczyWpOuDT0,36161
+langroid/agent/chat_agent.py,sha256=geQU3F20OoEU_OmfeHq1iEc4FWBiPBbFlkE40J27zoo,36157
 langroid/agent/chat_document.py,sha256=kbep6196vfTwEKNeMw6PB656W6wf-AFDT01IJxL9tIM,7181
 langroid/agent/helpers.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/agent/junk,sha256=LxfuuW7Cijsg0szAzT81OjWWv1PMNI-6w_-DspVIO2s,339
 langroid/agent/openai_assistant.py,sha256=yBtxis64XOnxtJzlkwUoTm-wCyvKr4DGo9-laXYMok0,32654
 langroid/agent/special/__init__.py,sha256=PLGt63iwNnSCCigRYcqicD8AUXwdV_HRUWffRHllUC4,510
 langroid/agent/special/doc_chat_agent.py,sha256=0XMUTyIAmL-looB_Xb6TsljoywiiDfF6GjgldlL2K3E,44585
-langroid/agent/special/lance_doc_chat_agent.py,sha256=xZvB4adgGBp8L79wi1Z77kGkZmTTJg8dZU60heeO5cc,7570
+langroid/agent/special/lance_doc_chat_agent.py,sha256=2qTERApPRr9OgQzb7KASw6SH5Xo8AKQfFHf7i2AZ4u8,7861
 langroid/agent/special/lance_rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/agent/special/lance_rag/critic_agent.py,sha256=9izW4keCxVZEqrFOgyVUHD7N1vTXLkRynXYYd1Vpwzw,5785
 langroid/agent/special/lance_rag/lance_rag_task.py,sha256=l_HQgrYY-CX2FwIsS961aEF3bYog3GDYo98fj0C0mSk,2889
@@ -18,7 +18,7 @@ langroid/agent/special/lance_rag/query_planner_agent.py,sha256=Tf0-70Di4mw1B6efS
 langroid/agent/special/relevance_extractor_agent.py,sha256=Z0OJmpCOESRX0Viar3JRcjjnDBhSA8useD1ZDflIo0s,4571
 langroid/agent/special/retriever_agent.py,sha256=uu6vqFg85uCVM-_DrXesYe2gH_-WcoHhlsKRlLuZPXk,1867
 langroid/agent/special/sql/__init__.py,sha256=3kR5nC0wnYIzmMrr9L8RJa7JAJpbwBLx7KKygiwz0v0,111
-langroid/agent/special/sql/sql_chat_agent.py,sha256=fU1nwlMu6RirsEvM9boIUkhDJborYnL9aXS9RkkTrnQ,12832
+langroid/agent/special/sql/sql_chat_agent.py,sha256=sFxApcIMc7u31aEZLV01Zrtn8ZLYHZ74kjWfOJpVKoA,12917
 langroid/agent/special/sql/utils/__init__.py,sha256=_IBHt3iNXvPqxvDrs5_T86qdj0gPugVGnGNi6Cx7F-I,238
 langroid/agent/special/sql/utils/description_extractors.py,sha256=GcQ82IhKPInS_3TOqRgD4iRUQt-Ez4WG9vNHsV0V85Q,4494
 langroid/agent/special/sql/utils/populate_metadata.py,sha256=zRjw31a1ZXvpx9bcmbtC2mngdHl-bp1ZNHStcPG8_Qk,2712
@@ -70,7 +70,7 @@ langroid/parsing/table_loader.py,sha256=qNM4obT_0Y4tjrxNBCNUYjKQ9oETCZ7FbolKBTcz
 langroid/parsing/url_loader.py,sha256=RZCX1RJuQpTatJjBOU74_gJ5Ab7xwarRmFh5ON4n_G4,2279
 langroid/parsing/url_loader_cookies.py,sha256=Lg4sNpRz9MByWq2mde6T0hKv68VZSV3mtMjNEHuFeSU,2327
 langroid/parsing/urls.py,sha256=Nv4yCWQLLBEjaiRdaZZVQNBEl_cfK_V6cVuPm91wGtU,7686
-langroid/parsing/utils.py,sha256=AaUt7mnQ-VNBI-pIDr-ZtprmeKHOv0LwdonaPxmI47g,7801
+langroid/parsing/utils.py,sha256=g5tRl0HWLXYzkiwYdMfreamzG76tK6ieiUqPNx35ln4,9845
 langroid/parsing/web_search.py,sha256=hGUVoSJNdpoT5rsm-ikAteMiUropHrzKaxN8EVVqO2U,2496
 langroid/prompts/__init__.py,sha256=aTW86CbDZM7tntqiTVeNLYJv7pbRDcKOI3qHVXCEHUY,99
 langroid/prompts/dialog.py,sha256=SpfiSyofSgy2pwD1YboHR_yHO3LEEMbv6j2sm874jKo,331
@@ -103,7 +103,7 @@ langroid/vector_store/meilisearch.py,sha256=d2huA9P-NoYRuAQ9ZeXJmMKr7ry8u90RUSR2
 langroid/vector_store/momento.py,sha256=j6Eo6oIDN2fe7lsBOlCXJn3uvvERHHTFL5QJfeREeOM,10044
 langroid/vector_store/qdrant_cloud.py,sha256=3im4Mip0QXLkR6wiqVsjV1QvhSElfxdFSuDKddBDQ-4,188
 langroid/vector_store/qdrantdb.py,sha256=qt7Dye6rcgoe0551WzmOxRGIlJfL87D4MX7HdqxuEok,13393
-langroid-0.1.160.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
-langroid-0.1.160.dist-info/METADATA,sha256=C2tjQ0HKr3e3x0iWWa6vrbraLd9qgHZuslb1nrN5ERA,42745
-langroid-0.1.160.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-langroid-0.1.160.dist-info/RECORD,,
+langroid-0.1.162.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
+langroid-0.1.162.dist-info/METADATA,sha256=j6ZBZx4nLwIX4NNMNpwu4iDYIxtD6lOFjTFZ3n53zic,42745
+langroid-0.1.162.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+langroid-0.1.162.dist-info/RECORD,,