llm-gemini 0.3a0__py3-none-any.whl → 0.4__py3-none-any.whl

{llm_gemini-0.3a0.dist-info → llm_gemini-0.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llm-gemini
-Version: 0.3a0
+Version: 0.4
 Summary: LLM plugin to access Google's Gemini family of models
 Author: Simon Willison
 License: Apache-2.0
@@ -11,11 +11,12 @@ Project-URL: CI, https://github.com/simonw/llm-gemini/actions
 Classifier: License :: OSI Approved :: Apache Software License
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: llm >=0.17a0
+Requires-Dist: llm >=0.17
 Requires-Dist: httpx
 Requires-Dist: ijson
 Provides-Extra: test
 Requires-Dist: pytest ; extra == 'test'
+Requires-Dist: pytest-recording ; extra == 'test'
 
 # llm-gemini
 
@@ -35,13 +36,13 @@ llm install llm-gemini
 ## Usage
 
 Configure the model by setting a key called "gemini" to your [API key](https://aistudio.google.com/app/apikey):
-
 ```bash
 llm keys set gemini
 ```
 ```
 <paste key here>
 ```
+You can also set the API key by assigning it to the environment variable `LLM_GEMINI_KEY`.
 
 Now run the model using `-m gemini-1.5-pro-latest`, for example:
 
@@ -55,16 +56,13 @@ llm -m gemini-1.5-pro-latest "A joke about a pelican and a walrus"
 >
 > The pelican taps its beak thoughtfully. "I believe," it says, "it's a billfish."
 
-To chat interactively with the model, run `llm chat`:
-
-```bash
-llm chat -m gemini-1.5-pro-latest
-```
-
 Other models are:
 
 - `gemini-1.5-flash-latest`
-- gemini-1.5-flash-8b-latest` - the least expensive
+- `gemini-1.5-flash-8b-latest` - the least expensive
+- `gemini-exp-1114` - recent experimental
+
+### Images, audio and video
 
 Gemini models are multi-modal. You can provide images, audio or video files as input like this:
 
@@ -76,8 +74,52 @@ Or with a URL:
 llm -m gemini-1.5-flash-8b-latest 'describe image' \
   -a https://static.simonwillison.net/static/2024/pelicans.jpg
 ```
+Audio works too:
+
+```bash
+llm -m gemini-1.5-pro-latest 'transcribe audio' -a audio.mp3
+```
+
+And video:
+
+```bash
+llm -m gemini-1.5-pro-latest 'describe what happens' -a video.mp4
+```
+The Gemini prompting guide includes [extensive advice](https://ai.google.dev/gemini-api/docs/file-prompting-strategies) on multi-modal prompting.
+
+### JSON output
+
+Use `-o json_object 1` to force the output to be JSON:
+
+```bash
+llm -m gemini-1.5-flash-latest -o json_object 1 \
+  '3 largest cities in California, list of {"name": "..."}'
+```
+Outputs:
+```json
+{"cities": [{"name": "Los Angeles"}, {"name": "San Diego"}, {"name": "San Jose"}]}
+```
+
+### Code execution
+
+Gemini models can [write and execute code](https://ai.google.dev/gemini-api/docs/code-execution) - they can decide to write Python code, execute it in a secure sandbox and use the result as part of their response.
+
+To enable this feature, use `-o code_execution 1`:
+
+```bash
+llm -m gemini-1.5-pro-latest -o code_execution 1 \
+'use python to calculate (factorial of 13) * 3'
+```
+
+### Chat
+
+To chat interactively with the model, run `llm chat`:
+
+```bash
+llm chat -m gemini-1.5-pro-latest
+```
 
-### Embeddings
+## Embeddings
 
 The plugin also adds support for the `text-embedding-004` embedding model.
 

llm_gemini-0.4.dist-info/RECORD

@@ -0,0 +1,7 @@
+llm_gemini.py,sha256=_7yQ14ffRpyK3ChAOc6M2ufylg2kUKTQK4C3VKOiUgM,10672
+llm_gemini-0.4.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+llm_gemini-0.4.dist-info/METADATA,sha256=rxQq1JCu1dvMwuVSXy8Tn1txFBdJX1NjCjdFJ6VEa1g,4862
+llm_gemini-0.4.dist-info/WHEEL,sha256=R06PA3UVYHThwHvxuRWMqaGcr-PuniXahwjmQRFMEkY,91
+llm_gemini-0.4.dist-info/entry_points.txt,sha256=n544bpgUPIBc5l_cnwsTxPc3gMGJHPtAyqBNp-CkMWk,26
+llm_gemini-0.4.dist-info/top_level.txt,sha256=WUQmG6_2QKbT_8W4HH93qyKl_0SUteL4Ra6_PhyNGKU,11
+llm_gemini-0.4.dist-info/RECORD,,

{llm_gemini-0.3a0.dist-info → llm_gemini-0.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.2.0)
+Generator: setuptools (75.5.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

llm_gemini.py

@@ -1,9 +1,9 @@
 import httpx
 import ijson
 import llm
-import urllib.parse
+from pydantic import Field
+from typing import Optional
 
-# We disable all of these to avoid random unexpected errors
 SAFETY_SETTINGS = [
     {
         "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
@@ -26,15 +26,20 @@ SAFETY_SETTINGS = [
 
 @llm.hookimpl
 def register_models(register):
-    register(GeminiPro("gemini-pro"))
-    register(GeminiPro("gemini-1.5-pro-latest"))
-    register(GeminiPro("gemini-1.5-flash-latest"))
-    register(GeminiPro("gemini-1.5-pro-001"))
-    register(GeminiPro("gemini-1.5-flash-001"))
-    register(GeminiPro("gemini-1.5-pro-002"))
-    register(GeminiPro("gemini-1.5-flash-002"))
-    register(GeminiPro("gemini-1.5-flash-8b-latest"))
-    register(GeminiPro("gemini-1.5-flash-8b-001"))
+    # Register both sync and async versions of each model
+    for model_id in [
+        "gemini-pro",
+        "gemini-1.5-pro-latest",
+        "gemini-1.5-flash-latest",
+        "gemini-1.5-pro-001",
+        "gemini-1.5-flash-001",
+        "gemini-1.5-pro-002",
+        "gemini-1.5-flash-002",
+        "gemini-1.5-flash-8b-latest",
+        "gemini-1.5-flash-8b-001",
+        "gemini-exp-1114",
+    ]:
+        register(GeminiPro(model_id), AsyncGeminiPro(model_id))
 
 
 def resolve_type(attachment):
@@ -45,7 +50,9 @@ def resolve_type(attachment):
     return mime_type
 
 
-class GeminiPro(llm.Model):
+class _SharedGemini:
+    needs_key = "gemini"
+    key_env_var = "LLM_GEMINI_KEY"
     can_stream = True
 
     attachment_types = (
@@ -75,8 +82,54 @@ class GeminiPro(llm.Model):
         "video/webm",
         "video/wmv",
         "video/3gpp",
+        "video/quicktime",
     )
 
+    class Options(llm.Options):
+        code_execution: Optional[bool] = Field(
+            description="Enables the model to generate and run Python code",
+            default=None,
+        )
+        temperature: Optional[float] = Field(
+            description=(
+                "Controls the randomness of the output. Use higher values for "
+                "more creative responses, and lower values for more "
+                "deterministic responses."
+            ),
+            default=None,
+            ge=0.0,
+            le=2.0,
+        )
+        max_output_tokens: Optional[int] = Field(
+            description="Sets the maximum number of tokens to include in a candidate.",
+            default=None,
+        )
+        top_p: Optional[float] = Field(
+            description=(
+                "Changes how the model selects tokens for output. Tokens are "
+                "selected from the most to least probable until the sum of "
+                "their probabilities equals the topP value."
+            ),
+            default=None,
+            ge=0.0,
+            le=1.0,
+        )
+        top_k: Optional[int] = Field(
+            description=(
+                "Changes how the model selects tokens for output. A topK of 1 "
+                "means the selected token is the most probable among all the "
+                "tokens in the model's vocabulary, while a topK of 3 means "
+                "that the next token is selected from among the 3 most "
+                "probable using the temperature."
+            ),
+            default=None,
+            ge=1,
+        )
+        json_object: Optional[bool] = Field(
+            description="Output a valid JSON object {...}",
+            default=None,
+        )
+
     def __init__(self, model_id):
         self.model_id = model_id
 
@@ -95,11 +148,14 @@ class GeminiPro(llm.Model):
                             }
                         }
                     )
-                parts.append({"text": response.prompt.prompt})
+                if response.prompt.prompt:
+                    parts.append({"text": response.prompt.prompt})
                 messages.append({"role": "user", "parts": parts})
                 messages.append({"role": "model", "parts": [{"text": response.text()}]})
 
-        parts = [{"text": prompt.prompt}]
+        parts = []
+        if prompt.prompt:
+            parts.append({"text": prompt.prompt})
         for attachment in prompt.attachments:
             mime_type = resolve_type(attachment)
             parts.append(
@@ -114,24 +170,59 @@ class GeminiPro(llm.Model):
         messages.append({"role": "user", "parts": parts})
         return messages
 
-    def execute(self, prompt, stream, response, conversation):
-        key = llm.get_key("", "gemini", "LLM_GEMINI_KEY")
-        url = "https://generativelanguage.googleapis.com/v1beta/models/{}:streamGenerateContent?".format(
-            self.model_id
-        ) + urllib.parse.urlencode(
-            {"key": key}
-        )
-        gathered = []
+    def build_request_body(self, prompt, conversation):
         body = {
             "contents": self.build_messages(prompt, conversation),
             "safetySettings": SAFETY_SETTINGS,
         }
+        if prompt.options and prompt.options.code_execution:
+            body["tools"] = [{"codeExecution": {}}]
         if prompt.system:
             body["systemInstruction"] = {"parts": [{"text": prompt.system}]}
+
+        config_map = {
+            "temperature": "temperature",
+            "max_output_tokens": "maxOutputTokens",
+            "top_p": "topP",
+            "top_k": "topK",
+        }
+        if prompt.options and prompt.options.json_object:
+            body["generationConfig"] = {"response_mime_type": "application/json"}
+
+        if any(
+            getattr(prompt.options, key, None) is not None for key in config_map.keys()
+        ):
+            generation_config = {}
+            for key, other_key in config_map.items():
+                config_value = getattr(prompt.options, key, None)
+                if config_value is not None:
+                    generation_config[other_key] = config_value
+            body["generationConfig"] = generation_config
+
+        return body
+
+    def process_part(self, part):
+        if "text" in part:
+            return part["text"]
+        elif "executableCode" in part:
+            return f'```{part["executableCode"]["language"].lower()}\n{part["executableCode"]["code"].strip()}\n```\n'
+        elif "codeExecutionResult" in part:
+            return f'```\n{part["codeExecutionResult"]["output"].strip()}\n```\n'
+        return ""
+
+
+class GeminiPro(_SharedGemini, llm.Model):
+    def execute(self, prompt, stream, response, conversation):
+        key = self.get_key()
+        url = f"https://generativelanguage.googleapis.com/v1beta/models/{self.model_id}:streamGenerateContent"
+        gathered = []
+        body = self.build_request_body(prompt, conversation)
+
         with httpx.stream(
             "POST",
             url,
             timeout=None,
+            headers={"x-goog-api-key": key},
             json=body,
         ) as http_response:
             events = ijson.sendable_list()
@@ -143,7 +234,8 @@ class GeminiPro(llm.Model):
                     if isinstance(event, dict) and "error" in event:
                         raise llm.ModelError(event["error"]["message"])
                     try:
-                        yield event["candidates"][0]["content"]["parts"][0]["text"]
+                        part = event["candidates"][0]["content"]["parts"][0]
+                        yield self.process_part(part)
                     except KeyError:
                         yield ""
                     gathered.append(event)
@@ -151,6 +243,39 @@ class GeminiPro(llm.Model):
         response.response_json = gathered
 
 
+class AsyncGeminiPro(_SharedGemini, llm.AsyncModel):
+    async def execute(self, prompt, stream, response, conversation):
+        key = self.get_key()
+        url = f"https://generativelanguage.googleapis.com/v1beta/models/{self.model_id}:streamGenerateContent"
+        gathered = []
+        body = self.build_request_body(prompt, conversation)
+
+        async with httpx.AsyncClient() as client:
+            async with client.stream(
+                "POST",
+                url,
+                timeout=None,
+                headers={"x-goog-api-key": key},
+                json=body,
+            ) as http_response:
+                events = ijson.sendable_list()
+                coro = ijson.items_coro(events, "item")
+                async for chunk in http_response.aiter_bytes():
+                    coro.send(chunk)
+                    if events:
+                        event = events[0]
+                        if isinstance(event, dict) and "error" in event:
+                            raise llm.ModelError(event["error"]["message"])
+                        try:
+                            part = event["candidates"][0]["content"]["parts"][0]
+                            yield self.process_part(part)
+                        except KeyError:
+                            yield ""
+                        gathered.append(event)
+                        events.clear()
+        response.response_json = gathered
+
+
 @llm.hookimpl
 def register_embedding_models(register):
     register(
@@ -170,6 +295,7 @@ class GeminiEmbeddingModel(llm.EmbeddingModel):
     def embed_batch(self, items):
         headers = {
             "Content-Type": "application/json",
+            "x-goog-api-key": self.get_key(),
         }
         data = {
             "requests": [
@@ -183,7 +309,7 @@ class GeminiEmbeddingModel(llm.EmbeddingModel):
 
         with httpx.Client() as client:
             response = client.post(
-                f"https://generativelanguage.googleapis.com/v1beta/models/{self.gemini_model_id}:batchEmbedContents?key={self.get_key()}",
+                f"https://generativelanguage.googleapis.com/v1beta/models/{self.gemini_model_id}:batchEmbedContents",
                 headers=headers,
                 json=data,
                 timeout=None,

llm_gemini-0.3a0.dist-info/RECORD

@@ -1,7 +0,0 @@
-llm_gemini.py,sha256=nmatZLQyVUUwoaiUloPycKKDbLMzGo4mcXeJwjzAENA,5881
-llm_gemini-0.3a0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-llm_gemini-0.3a0.dist-info/METADATA,sha256=pIxt4pF2XgDJSVi2RNuaOc4fgU2pRYWnasijmry8d_E,3618
-llm_gemini-0.3a0.dist-info/WHEEL,sha256=OVMc5UfuAQiSplgO0_WdW7vXVGAt9Hdd6qtN4HotdyA,91
-llm_gemini-0.3a0.dist-info/entry_points.txt,sha256=n544bpgUPIBc5l_cnwsTxPc3gMGJHPtAyqBNp-CkMWk,26
-llm_gemini-0.3a0.dist-info/top_level.txt,sha256=WUQmG6_2QKbT_8W4HH93qyKl_0SUteL4Ra6_PhyNGKU,11
-llm_gemini-0.3a0.dist-info/RECORD,,