langroid 0.41.3__py3-none-any.whl → 0.41.5__py3-none-any.whl

langroid/embedding_models/models.py

@@ -450,9 +450,9 @@ class LlamaCppServerEmbeddings(EmbeddingModel):
 class GeminiEmbeddings(EmbeddingModel):
     def __init__(self, config: GeminiEmbeddingsConfig = GeminiEmbeddingsConfig()):
         try:
-            import google.generativeai as genai
+            from google import genai
         except ImportError as e:
-            raise LangroidImportError(extra="google-generativeai", error=str(e))
+            raise LangroidImportError(extra="google-genai", error=str(e))
         super().__init__()
         self.config = config
         load_dotenv()
@@ -464,29 +464,30 @@ class GeminiEmbeddings(EmbeddingModel):
                 GEMINI_API_KEY env variable must be set to use GeminiEmbeddings.
                 """
             )
-        genai.configure(api_key=self.config.api_key)  # type: ignore[attr-defined]
-        self.client = genai
+        self.client = genai.Client(api_key=self.config.api_key)
 
     def embedding_fn(self) -> Callable[[List[str]], Embeddings]:
         return EmbeddingFunctionCallable(self, self.config.batch_size)
 
-    def generate_embeddings(self, texts: List[str]) -> Embeddings:
-        all_embeddings = []  # More precise type hint
+    def generate_embeddings(self, texts: List[str]) -> List[List[float]]:
+        """Generates embeddings for a list of input texts."""
+        all_embeddings: List[List[float]] = []
+
         for batch in batched(texts, self.config.batch_size):
-            result = self.client.embed_content(  # type: ignore[attr-defined]
+            result = self.client.models.embed_content(  # type: ignore[attr-defined]
                 model=self.config.model_name,
-                content=batch,
-                task_type="RETRIEVAL_DOCUMENT",
+                contents=batch,
             )
 
-            embeddings = result["embedding"]
-            if not isinstance(embeddings, list):
-                raise ValueError("Unexpected format for embeddings: not a list")
+            if not hasattr(result, "embeddings") or not isinstance(
+                result.embeddings, list
+            ):
+                raise ValueError(
+                    "Unexpected format for embeddings: missing or incorrect type"
+                )
 
-            if embeddings and isinstance(embeddings[0], list):
-                all_embeddings.extend(embeddings)
-            else:
-                all_embeddings.append(embeddings)
+            # Extract .values from ContentEmbedding objects
+            all_embeddings.extend([emb.values for emb in result.embeddings])
 
         return all_embeddings
 

langroid/language_models/model_info.py

@@ -64,6 +64,7 @@ class GeminiModel(ModelName):
     GEMINI_1_5_FLASH_8B = "gemini/gemini-1.5-flash-8b"
     GEMINI_1_5_PRO = "gemini/gemini-1.5-pro"
     GEMINI_2_FLASH = "gemini/gemini-2.0-flash"
+    GEMINI_2_FLASH_LITE = "gemini/gemini-2.0-flash-lite-preview"
     GEMINI_2_FLASH_THINKING = "gemini/gemini-2.0-flash-thinking-exp"
 
 
@@ -282,9 +283,21 @@ MODEL_INFO: Dict[str, ModelInfo] = {
         provider=ModelProvider.GOOGLE,
         context_length=1_056_768,
         max_output_tokens=8192,
+        input_cost_per_million=0.10,
+        output_cost_per_million=0.40,
         rename_params={"max_tokens": "max_completion_tokens"},
         description="Gemini 2.0 Flash",
     ),
+    GeminiModel.GEMINI_2_FLASH_LITE.value: ModelInfo(
+        name=GeminiModel.GEMINI_2_FLASH_LITE.value,
+        provider=ModelProvider.GOOGLE,
+        context_length=1_056_768,
+        max_output_tokens=8192,
+        input_cost_per_million=0.075,
+        output_cost_per_million=0.30,
+        rename_params={"max_tokens": "max_completion_tokens"},
+        description="Gemini 2.0 Flash Lite Preview",
+    ),
     GeminiModel.GEMINI_1_5_FLASH.value: ModelInfo(
         name=GeminiModel.GEMINI_1_5_FLASH.value,
         provider=ModelProvider.GOOGLE,

langroid/vector_store/weaviatedb.py

@@ -45,6 +45,9 @@ class WeaviateDBConfig(VectorStoreConfig):
     embedding: EmbeddingModelsConfig = OpenAIEmbeddingsConfig()
     distance: str = VectorDistances.COSINE
     cloud: bool = False
+    docker: bool = False
+    host: str = "127.0.0.1"
+    port: int = 8080
     storage_path: str = ".weaviate_embedded/data"
 
 
@@ -55,11 +58,13 @@ class WeaviateDB(VectorStore):
             raise LangroidImportError("weaviate", "weaviate")
         self.config: WeaviateDBConfig = config
         load_dotenv()
-        if not self.config.cloud:
-            self.client = weaviate.connect_to_embedded(
-                version="latest", persistence_data_path=self.config.storage_path
+        if self.config.docker:
+            self.client = weaviate.connect_to_local(
+                host=self.config.host,
+                port=self.config.port,
             )
-        else:  # Cloud mode
+            self.config.cloud = False
+        elif self.config.cloud:
             key = os.getenv("WEAVIATE_API_KEY")
             url = os.getenv("WEAVIATE_API_URL")
             if url is None or key is None:
@@ -73,6 +78,10 @@ class WeaviateDB(VectorStore):
                 cluster_url=url,
                 auth_credentials=Auth.api_key(key),
             )
+        else:
+            self.client = weaviate.connect_to_embedded(
+                version="latest", persistence_data_path=self.config.storage_path
+            )
 
         if config.collection_name is not None:
             WeaviateDB.validate_and_format_collection_name(config.collection_name)

{langroid-0.41.3.dist-info → langroid-0.41.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langroid
-Version: 0.41.3
+Version: 0.41.5
 Summary: Harness LLMs with Multi-Agent Programming
 Author-email: Prasad Chalasani <pchalasani@gmail.com>
 License: MIT
@@ -21,7 +21,7 @@ Requires-Dist: fakeredis<3.0.0,>=2.12.1
 Requires-Dist: fire<1.0.0,>=0.5.0
 Requires-Dist: gitpython<4.0.0,>=3.1.43
 Requires-Dist: google-api-python-client<3.0.0,>=2.95.0
-Requires-Dist: google-generativeai<1.0.0,>=0.5.2
+Requires-Dist: google-genai>=1.0.0
 Requires-Dist: groq<1.0.0,>=0.13.0
 Requires-Dist: grpcio<2.0.0,>=1.62.1
 Requires-Dist: halo<1.0.0,>=0.0.31
@@ -112,8 +112,10 @@ Provides-Extra: exa
 Requires-Dist: exa-py>=1.8.7; extra == 'exa'
 Provides-Extra: fastembed
 Requires-Dist: fastembed<0.4.0,>=0.3.1; extra == 'fastembed'
+Provides-Extra: google-genai
+Requires-Dist: google-genai>=1.0.0; extra == 'google-genai'
 Provides-Extra: google-generativeai
-Requires-Dist: google-generativeai>=0.8.4; extra == 'google-generativeai'
+Requires-Dist: google-genai>=1.0.0; extra == 'google-generativeai'
 Provides-Extra: hf-embeddings
 Requires-Dist: sentence-transformers<3.0.0,>=2.2.2; extra == 'hf-embeddings'
 Requires-Dist: torch<3.0.0,>=2.0.0; extra == 'hf-embeddings'
@@ -319,7 +321,7 @@ teacher_task.run()
 - **Jan 2025:**
   - [0.36.0](https://github.com/langroid/langroid/releases/tag/0.36.0): Weaviate vector-db support (thanks @abab-dev).
   - [0.35.0](https://github.com/langroid/langroid/releases/tag/0.35.0): Capture/Stream reasoning content from 
-    Reasoning LLMs (e.g. DeepSeek, OpenAI o1) in addition to final answer.
+    Reasoning LLMs (e.g. DeepSeek-R1, OpenAI o1) in addition to final answer.
   - [0.34.0](https://github.com/langroid/langroid/releases/tag/0.34.0): DocChatAgent 
     chunk enrichment to improve retrieval. (collaboration with @dfm88). 
   - [0.33.0](https://github.com/langroid/langroid/releases/tag/0.33.3) Move from Poetry to uv! (thanks @abab-dev).
@@ -627,7 +629,7 @@ For many practical scenarios, you may need additional optional dependencies:
 - For "chat with databases", use the `db` extra:
     ```bash
     pip install "langroid[db]"
-    ``
+    ```
 - You can specify multiple extras by separating them with commas, e.g.:
     ```bash
     pip install "langroid[doc-chat,db]"

{langroid-0.41.3.dist-info → langroid-0.41.5.dist-info}/RECORD

@@ -59,7 +59,7 @@ langroid/cachedb/momento_cachedb.py,sha256=YEOJ62hEcV6iIeMr5aGgRYgWQqFYaej9gEDEc
 langroid/cachedb/redis_cachedb.py,sha256=7kgnbf4b5CKsCrlL97mHWKvdvlLt8zgn7lc528jEpiE,5141
 langroid/embedding_models/__init__.py,sha256=KyYxR3jDFUCfYjSuCL86qjAmrq6mXXjOT4lFNOKVj6Y,955
 langroid/embedding_models/base.py,sha256=Ml7oA6PzQm0wZmIYn3fhF7dvZCi-amviWUwOeBegH3A,2562
-langroid/embedding_models/models.py,sha256=fKQBiaaG7uYoeELDbAiNxwLdn-CWN8dyiVEZcdk_bjI,18959
+langroid/embedding_models/models.py,sha256=93rQjvcltGLDYbgT1TIW8PZiAbNPAvPAqxCLlLS9GAo,18955
 langroid/embedding_models/remote_embeds.py,sha256=6_kjXByVbqhY9cGwl9R83ZcYC2km-nGieNNAo1McHaY,5151
 langroid/embedding_models/protoc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/embedding_models/protoc/embeddings.proto,sha256=_O-SgFpTaylQeOTgSpxhEJ7CUw7PeCQQJLaPqpPYKJg,321
@@ -71,7 +71,7 @@ langroid/language_models/azure_openai.py,sha256=zNQzzsERxNestq-hFfQZbvTzK43G2vjR
 langroid/language_models/base.py,sha256=is4l3x858tdPHbrJU2jxJXe2j9PCGb9kk_c5nyfShxs,26150
 langroid/language_models/config.py,sha256=9Q8wk5a7RQr8LGMT_0WkpjY8S4ywK06SalVRjXlfCiI,378
 langroid/language_models/mock_lm.py,sha256=5BgHKDVRWFbUwDT_PFgTZXz9-k8wJSA2e3PZmyDgQ1k,4022
-langroid/language_models/model_info.py,sha256=yKAaKoCanPoqaoHCzRVNPjg-M9a4S2Vm2AJGnwMeO-M,11360
+langroid/language_models/model_info.py,sha256=GEIyfypSzuev6ZG81-nb8OhvSxH4PHQ_m5UhBAQ8kSA,11910
 langroid/language_models/openai_gpt.py,sha256=aajZ3ZvGkwI-3QdsNWgJ4QSyGpnyXJ5n4p2fYGUmdo4,77317
 langroid/language_models/utils.py,sha256=L4_CbihDMTGcsg0TOG1Yd5JFEto46--h7CX_14m89sQ,5016
 langroid/language_models/prompt_formatter/__init__.py,sha256=2-5cdE24XoFDhifOLl8yiscohil1ogbP1ECkYdBlBsk,372
@@ -127,8 +127,8 @@ langroid/vector_store/momento.py,sha256=xOaU7Hlyyn_5ihb0ARS5JHtmrKrTCt2IdRA-ioMM
 langroid/vector_store/pineconedb.py,sha256=otxXZNaBKb9f_H75HTaU3lMHiaR2NUp5MqwLZXpEY9M,14994
 langroid/vector_store/postgres.py,sha256=DQHd6dt-OcV_QVNm-ymn28rlTfhI6hqgcpLTPCsm0jI,15990
 langroid/vector_store/qdrantdb.py,sha256=v7TAsIoj_vxeKDYS9tpwJLBZA8fuTweTYxHo0X_uawM,17949
-langroid/vector_store/weaviatedb.py,sha256=ONEr2iGS0Ii73oMe7tRk6bB-BEXQUa70fYSrdI8d3yo,11481
-langroid-0.41.3.dist-info/METADATA,sha256=hQDjq_z2rXui7guy7-_TweJvkSkGWhQ-iQZb5i0vyIk,61259
-langroid-0.41.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-langroid-0.41.3.dist-info/licenses/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
-langroid-0.41.3.dist-info/RECORD,,
+langroid/vector_store/weaviatedb.py,sha256=tjlqEtkwrhykelt-nbr2WIuHWJBuSAGjZuG6gsAMBsc,11753
+langroid-0.41.5.dist-info/METADATA,sha256=Ii6nQYMNZlMmeJ27AVkt7m6d5useGfOXIunF3BAlVzI,61331
+langroid-0.41.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+langroid-0.41.5.dist-info/licenses/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
+langroid-0.41.5.dist-info/RECORD,,